[PATCH] ARM: Add SWP/SWPB emulation for ARMv7 processors (v3)
Leif Lindholm
leif.lindholm at arm.com
Tue Jan 5 13:24:47 EST 2010
The SWP instruction was deprecated in the ARMv6 architecture, superseded
by the LDREX/STREX family of instructions for
load-linked/store-conditional operations. The ARMv7 multiprocessing
extensions mandate that SWP/SWPB instructions are treated as undefined
from reset, with the ability to enable them through the System Control
Register SW bit.
This patch adds the alternative solution to emulate the SWP and SWPB
instructions using LDREX/STREX sequences, and log statistics to
/proc/cpu/swp_emulation. To correctly deal with copy-on-write, it also
modifies cpu_v7_set_pte_ext to change the mappings to priviliged RO when
user RO.
Signed-off-by: Leif Lindholm <leif.lindholm at arm.com>
Cc: Catalin Marinas <catalin.marinas at arm.com>
---
arch/arm/kernel/Makefile | 1
arch/arm/kernel/swp_emulate.c | 297 +++++++++++++++++++++++++++++++++++++++++
arch/arm/mm/Kconfig | 20 +++
arch/arm/mm/proc-v7.S | 6 +
4 files changed, 324 insertions(+), 0 deletions(-)
create mode 100644 arch/arm/kernel/swp_emulate.c
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index dd00f74..d1befbc 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -38,6 +38,7 @@ obj-$(CONFIG_ARM_THUMBEE) += thumbee.o
obj-$(CONFIG_KGDB) += kgdb.o
obj-$(CONFIG_ARM_UNWIND) += unwind.o
obj-$(CONFIG_HAVE_TCM) += tcm.o
+obj-$(CONFIG_SWP_EMULATE) += swp_emulate.o
obj-$(CONFIG_CRUNCH) += crunch.o crunch-bits.o
AFLAGS_crunch-bits.o := -Wa,-mcpu=ep9312
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
new file mode 100644
index 0000000..c77040e
--- /dev/null
+++ b/arch/arm/kernel/swp_emulate.c
@@ -0,0 +1,297 @@
+/*
+ * linux/arch/arm/kernel/swp_emulate.c
+ *
+ * Copyright (C) 2009 ARM Limited
+ * __user_* functions adapted from include/asm/uaccess.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Implements emulation of the SWP/SWPB instructions using load-exclusive and
+ * store-exclusive for processors that have them disabled (or future ones that
+ * might not implement them).
+ *
+ * Syntax of SWP{B} instruction: SWP{B}<c> <Rt>, <Rt2>, [<Rn>]
+ * Where: Rt = destination
+ * Rt2 = source
+ * Rn = address
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/syscalls.h>
+
+#include <asm/traps.h>
+#include <asm/uaccess.h>
+
+/*
+ * Error-checking SWP macros implemented using ldrex{b}/strex{b}
+ */
+#define __user_swp_asm(data, addr, res) \
+ __asm__ __volatile__( \
+ " mov r3, %1\n" \
+ "0: ldrex %1, [%2]\n" \
+ "1: strex %0, r3, [%2]\n" \
+ " cmp %0, #0\n" \
+ " movne %0, %3\n" \
+ "2:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .align 2\n" \
+ "3: mov %0, %4\n" \
+ " b 2b\n" \
+ " .previous\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .align 3\n" \
+ " .long 0b, 3b\n" \
+ " .long 1b, 3b\n" \
+ " .previous" \
+ : "=&r" (res), "+r" (data) \
+ : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT) \
+ : "cc", "r3")
+
+#define __user_swpb_asm(data, addr, res) \
+ __asm__ __volatile__( \
+ " mov r3, %1\n" \
+ "0: ldrexb %1, [%2]\n" \
+ "1: strexb %0, r3, [%2]\n" \
+ " cmp %0, #0\n" \
+ " movne %0, %3\n" \
+ "2:\n" \
+ " .section .fixup,\"ax\"\n" \
+ " .align 2\n" \
+ "3: mov %0, %4\n" \
+ " b 2b\n" \
+ " .previous\n" \
+ " .section __ex_table,\"a\"\n" \
+ " .align 3\n" \
+ " .long 0b, 3b\n" \
+ " .long 1b, 3b\n" \
+ " .previous" \
+ : "=&r" (res), "+r" (data) \
+ : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT) \
+ : "cc", "r3")
+
+/*
+ * Macros/defines for extracting register numbers from instruction.
+ */
+#define EXTRACT_REG_NUM(instruction, offset) \
+ (((instruction) & (0xf << (offset))) >> (offset))
+#define RN_OFFSET 16
+#define RT_OFFSET 12
+#define RT2_OFFSET 0
+
+static unsigned int swpcounter;
+static unsigned int swpbcounter;
+static unsigned int abtcounter;
+static long previous_pid;
+
+#ifdef CONFIG_PROC_FS
+static int proc_read_status(char *page, char **start, off_t off, int count,
+ int *eof, void *data)
+{
+ char *p = page;
+ int len;
+
+ p += sprintf(p, "Emulated SWP:\t\t%u\n", swpcounter);
+ p += sprintf(p, "Emulated SWPB:\t\t%u\n", swpbcounter);
+ p += sprintf(p, "Aborted SWP{B}:\t\t%u\n", abtcounter);
+ if (previous_pid != 0)
+ p += sprintf(p, "Last process:\t\t%ld\n", previous_pid);
+
+ len = (p - page) - off;
+ if (len < 0)
+ len = 0;
+
+ *eof = (len <= count) ? 1 : 0;
+ *start = page + off;
+
+ return len;
+}
+#endif
+
+/*
+ * Set up process info to signal segmentation fault - called on access error.
+ */
+static void set_segfault(struct pt_regs *regs, unsigned long addr)
+{
+ siginfo_t info;
+
+ if (find_vma(current->mm, addr) == NULL)
+ info.si_code = SEGV_MAPERR;
+ else
+ info.si_code = SEGV_ACCERR;
+
+ info.si_signo = SIGSEGV;
+ info.si_errno = 0;
+ info.si_addr = (void __user *)regs->ARM_pc;
+
+ pr_debug("SWP{B} emulation: access caused memory abort!\n");
+ arm_notify_die("Illegal memory access", regs, &info, 0, 0);
+
+ if (abtcounter == UINT_MAX)
+ printk(KERN_WARNING \
+ "SWP{B} emulation abort counter wrapped!\n");
+ abtcounter++;
+}
+
+static int emulate_swp(struct pt_regs *regs, unsigned int address,
+ unsigned int destreg, unsigned int data)
+{
+ unsigned int res = 0;
+
+ if (address & 0x3) {
+ /* SWP to unaligned address not permitted */
+ pr_debug("SWP instruction on unaligned pointer!\n");
+ return -EFAULT;
+ }
+
+ do {
+ if (res == -EAGAIN)
+ cond_resched();
+
+ smp_mb();
+ __user_swp_asm(data, address, res);
+ } while ((res == -EAGAIN) && !signal_pending(current));
+
+ if (res == 0) {
+ smp_mb();
+ regs->uregs[destreg] = data;
+ if (swpcounter == UINT_MAX)
+ printk(KERN_WARNING \
+ "SWP emulation counter wrapped!\n");
+ swpcounter++;
+ }
+
+ return res;
+}
+
+static int emulate_swpb(struct pt_regs *regs, unsigned int address,
+ unsigned int destreg, unsigned int data)
+{
+ unsigned int res = 0;
+
+ do {
+ if (res == -EAGAIN)
+ cond_resched();
+
+ smp_mb();
+ __user_swpb_asm(data, address, res);
+ } while ((res == -EAGAIN) && !signal_pending(current));
+
+ if (res == 0) {
+ smp_mb();
+ regs->uregs[destreg] = data;
+ if (swpbcounter == UINT_MAX)
+ printk(KERN_WARNING \
+ "SWPB emulation counter wrapped!\n");
+ swpbcounter++;
+ }
+
+ return res;
+}
+
+/*
+ * swp_handler logs the id of calling process, dissects the instruction, sanity
+ * checks the memory location, calls dedicated functions for SWP/SWPB and deals
+ * with fixup/error handling before returning
+ */
+static int swp_handler(struct pt_regs *regs, unsigned int instr)
+{
+ unsigned int address, destreg, data;
+ unsigned int res = 0;
+
+ if (current->pid != previous_pid) {
+ pr_debug("\"%s\" (%ld) uses deprecated SWP{B} instruction\n",
+ current->comm, (unsigned long)current->pid);
+ previous_pid = current->pid;
+ }
+
+ address = regs->uregs[EXTRACT_REG_NUM(instr, RN_OFFSET)];
+ data = regs->uregs[EXTRACT_REG_NUM(instr, RT2_OFFSET)];
+ destreg = EXTRACT_REG_NUM(instr, RT_OFFSET);
+
+ pr_debug("addr in r%d->0x%08x, dest is r%d, source in r%d->0x%08x)\n",
+ EXTRACT_REG_NUM(instr, RN_OFFSET), address,
+ destreg, EXTRACT_REG_NUM(instr, RT2_OFFSET), data);
+
+ /* Check access in reasonable access range for both SWP and SWPB */
+ if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) {
+ pr_debug("SWP{B} emulation: access to %p not allowed!\n",
+ (void *)address);
+ res = -EFAULT;
+ } else {
+ /*
+ * Bit 22 of the instruction distinguishes between the SWP and
+ * SWPB variants (bit set means SWPB).
+ */
+ if ((instr & (1 << 22)) == 0)
+ res = emulate_swp(regs, address, destreg, data);
+ else
+ res = emulate_swpb(regs, address, destreg, data);
+ }
+
+ if (res == 0) {
+ /*
+ * On successful emulation, revert the adjustment to the PC
+ * made in kernel/traps.c in order to resume execution at the
+ * instruction following the SWP{B}.
+ */
+ regs->ARM_pc += 4;
+ } else if (res == -EFAULT) {
+ /*
+ * Memory errors do not mean emulation failed.
+ * Set up signal info to return SEGV, then return OK
+ */
+ set_segfault(regs, address);
+ }
+
+ return 0;
+}
+
+/*
+ * Only emulate SWP/SWPB executed in ARM state/User mode.
+ * The kernel must be SWP free and SWP{B} does not exist in Thumb/ThumbEE.
+ */
+static struct undef_hook swp_hook = {
+ .instr_mask = 0x0fb00ff0,
+ .instr_val = 0x01000090,
+ .cpsr_mask = MODE_MASK | PSR_T_BIT | PSR_J_BIT,
+ .cpsr_val = USR_MODE,
+ .fn = swp_handler
+};
+
+/*
+ * Register handler and create status file in /proc/cpu
+ * Invoked as late_initcall, since not needed before init spawned.
+ */
+static int __init swp_emulation_init(void)
+{
+#ifdef CONFIG_PROC_FS
+ struct proc_dir_entry *res;
+
+#ifndef CONFIG_ALIGNMENT_TRAP
+ res = proc_mkdir("cpu", NULL);
+ if (!res)
+ return -ENOMEM;
+
+ res = create_proc_entry("swp_emulation", S_IRUGO, res);
+#else
+ res = create_proc_entry("cpu/swp_emulation", S_IRUGO, NULL);
+#endif
+
+ if (!res)
+ return -ENOMEM;
+
+ res->read_proc = proc_read_status;
+#endif /* CONFIG_PROC_FS */
+
+ printk(KERN_NOTICE "Registering SWP/SWPB emulation handler\n");
+ register_undef_hook(&swp_hook);
+
+ return 0;
+}
+
+late_initcall(swp_emulation_init);
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index dd4698c..c45b0d3 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -630,6 +630,26 @@ config ARM_THUMBEE
Say Y here if you have a CPU with the ThumbEE extension and code to
make use of it. Say N for code that can run on CPUs without ThumbEE.
+config SWP_EMULATE
+ bool "Emulate SWP/SWPB instructions"
+ depends on CPU_V7
+ default y if SMP
+ help
+ ARMv6 architecture deprecates use of the SWP/SWPB instructions.
+ ARMv7 multiprocessing extensions introduce the ability to disable
+ these instructions, triggering an undefined instruction exception
+ when executed. Say Y here to enable software emulation of these
+ instructions for userspace (not kernel) using LDREX/STREX.
+ Also creates /proc/cpu/swp_emulation for statistics.
+
+ NOTE: when accessing uncached shared regions, LDREX/STREX rely
+ on an external transaction monitoring block called a global
+ monitor to maintain update atomicity. If your system does not
+ implement a global monitor, this option can cause programs that
+ are map uncached memory to deadlock.
+
+ If unsure, say Y.
+
config CPU_BIG_ENDIAN
bool "Build big-endian kernel"
depends on ARCH_SUPPORTS_BIG_ENDIAN
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 3a28521..cb85aeb 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -147,8 +147,10 @@ ENTRY(cpu_v7_set_pte_ext)
tst r1, #L_PTE_USER
orrne r3, r3, #PTE_EXT_AP1
+#ifndef CONFIG_SWP_EMULATE
tstne r3, #PTE_EXT_APX
bicne r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
tst r1, #L_PTE_EXEC
orreq r3, r3, #PTE_EXT_XN
@@ -275,6 +277,10 @@ __v7_setup:
#ifdef CONFIG_CPU_ENDIAN_BE8
orr r6, r6, #1 << 25 @ big-endian page tables
#endif
+#ifdef CONFIG_SWP_EMULATE
+ orr r5, r5, #(1 << 10) @ set SW bit in "clear"
+ bic r6, r6, #(1 << 10) @ clear it in "mmuset"
+#endif
mrc p15, 0, r0, c1, c0, 0 @ read control register
bic r0, r0, r5 @ clear bits them
orr r0, r0, r6 @ set them
More information about the linux-arm-kernel
mailing list