summaryrefslogtreecommitdiffstats
path: root/arch/arm/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/kernel')
-rw-r--r--arch/arm/kernel/Makefile1
-rw-r--r--arch/arm/kernel/entry-common.S4
-rw-r--r--arch/arm/kernel/entry-v7m.S13
-rw-r--r--arch/arm/kernel/head-nommu.S2
-rw-r--r--arch/arm/kernel/head.S44
-rw-r--r--arch/arm/kernel/module-plts.c183
-rw-r--r--arch/arm/kernel/module.c32
-rw-r--r--arch/arm/kernel/module.lds4
-rw-r--r--arch/arm/kernel/perf_event_cpu.c12
-rw-r--r--arch/arm/kernel/setup.c30
-rw-r--r--arch/arm/kernel/smp.c10
-rw-r--r--arch/arm/kernel/tcm.c104
-rw-r--r--arch/arm/kernel/traps.c8
13 files changed, 405 insertions, 42 deletions
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 752725d..32c0990 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_CPU_IDLE) += cpuidle.o
obj-$(CONFIG_ISA_DMA_API) += dma.o
obj-$(CONFIG_FIQ) += fiq.o fiqasm.o
obj-$(CONFIG_MODULES) += armksyms.o module.o
+obj-$(CONFIG_ARM_MODULE_PLTS) += module-plts.o
obj-$(CONFIG_ISA_DMA) += dma-isa.o
obj-$(CONFIG_PCI) += bios32.o isa.o
obj-$(CONFIG_ARM_CPU_SUSPEND) += sleep.o suspend.o
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index f8ccc21..4e7f40c 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -33,7 +33,9 @@ ret_fast_syscall:
UNWIND(.fnstart )
UNWIND(.cantunwind )
disable_irq @ disable interrupts
- ldr r1, [tsk, #TI_FLAGS]
+ ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
+ tst r1, #_TIF_SYSCALL_WORK
+ bne __sys_trace_return
tst r1, #_TIF_WORK_MASK
bne fast_work_pending
asm_trace_hardirqs_on
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index 8944f49..b6c8bb9 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -117,9 +117,14 @@ ENTRY(__switch_to)
ENDPROC(__switch_to)
.data
- .align 8
+#if CONFIG_CPU_V7M_NUM_IRQ <= 112
+ .align 9
+#else
+ .align 10
+#endif
+
/*
- * Vector table (64 words => 256 bytes natural alignment)
+ * Vector table (Natural alignment need to be ensured)
*/
ENTRY(vector_table)
.long 0 @ 0 - Reset stack pointer
@@ -138,6 +143,6 @@ ENTRY(vector_table)
.long __invalid_entry @ 13 - Reserved
.long __pendsv_entry @ 14 - PendSV
.long __invalid_entry @ 15 - SysTick
- .rept 64 - 16
- .long __irq_entry @ 16..64 - External Interrupts
+ .rept CONFIG_CPU_V7M_NUM_IRQ
+ .long __irq_entry @ External Interrupts
.endr
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index aebfbf7..84da14b 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -123,7 +123,7 @@ ENTRY(secondary_startup)
ENDPROC(secondary_startup)
ENTRY(__secondary_switched)
- ldr sp, [r7, #8] @ set up the stack pointer
+ ldr sp, [r7, #12] @ set up the stack pointer
mov fp, #0
b secondary_start_kernel
ENDPROC(__secondary_switched)
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 3637973..e13c9cb 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -131,13 +131,30 @@ ENTRY(stext)
* The following calls CPU specific code in a position independent
* manner. See arch/arm/mm/proc-*.S for details. r10 = base of
* xxx_proc_info structure selected by __lookup_processor_type
- * above. On return, the CPU will be ready for the MMU to be
- * turned on, and r0 will hold the CPU control register value.
+ * above.
+ *
+ * The processor init function will be called with:
+ * r1 - machine type
+ * r2 - boot data (atags/dt) pointer
+ * r4 - translation table base (low word)
+ * r5 - translation table base (high word, if LPAE)
+ * r8 - translation table base 1 (pfn if LPAE)
+ * r9 - cpuid
+ * r13 - virtual address for __enable_mmu -> __turn_mmu_on
+ *
+ * On return, the CPU will be ready for the MMU to be turned on,
+ * r0 will hold the CPU control register value, r1, r2, r4, and
+ * r9 will be preserved. r5 will also be preserved if LPAE.
*/
ldr r13, =__mmap_switched @ address to jump to after
@ mmu has been enabled
adr lr, BSYM(1f) @ return (PIC) address
+#ifdef CONFIG_ARM_LPAE
+ mov r5, #0 @ high TTBR0
+ mov r8, r4, lsr #12 @ TTBR1 is swapper_pg_dir pfn
+#else
mov r8, r4 @ set TTBR1 to swapper_pg_dir
+#endif
ldr r12, [r10, #PROCINFO_INITFUNC]
add r12, r12, r10
ret r12
@@ -158,7 +175,7 @@ ENDPROC(stext)
*
* Returns:
* r0, r3, r5-r7 corrupted
- * r4 = page table (see ARCH_PGD_SHIFT in asm/memory.h)
+ * r4 = physical page table address
*/
__create_page_tables:
pgtbl r4, r8 @ page table address
@@ -333,7 +350,6 @@ __create_page_tables:
#endif
#ifdef CONFIG_ARM_LPAE
sub r4, r4, #0x1000 @ point to the PGD table
- mov r4, r4, lsr #ARCH_PGD_SHIFT
#endif
ret lr
ENDPROC(__create_page_tables)
@@ -346,8 +362,8 @@ __turn_mmu_on_loc:
#if defined(CONFIG_SMP)
.text
-ENTRY(secondary_startup_arm)
.arm
+ENTRY(secondary_startup_arm)
THUMB( adr r9, BSYM(1f) ) @ Kernel is entered in ARM.
THUMB( bx r9 ) @ If this is a Thumb-2 kernel,
THUMB( .thumb ) @ switch to Thumb now.
@@ -381,9 +397,9 @@ ENTRY(secondary_startup)
adr r4, __secondary_data
ldmia r4, {r5, r7, r12} @ address to jump to after
sub lr, r4, r5 @ mmu has been enabled
- ldr r4, [r7, lr] @ get secondary_data.pgdir
- add r7, r7, #4
- ldr r8, [r7, lr] @ get secondary_data.swapper_pg_dir
+ add r3, r7, lr
+ ldrd r4, [r3, #0] @ get secondary_data.pgdir
+ ldr r8, [r3, #8] @ get secondary_data.swapper_pg_dir
adr lr, BSYM(__enable_mmu) @ return address
mov r13, r12 @ __secondary_switched address
ldr r12, [r10, #PROCINFO_INITFUNC]
@@ -397,7 +413,7 @@ ENDPROC(secondary_startup_arm)
* r6 = &secondary_data
*/
ENTRY(__secondary_switched)
- ldr sp, [r7, #4] @ get secondary_data.stack
+ ldr sp, [r7, #12] @ get secondary_data.stack
mov fp, #0
b secondary_start_kernel
ENDPROC(__secondary_switched)
@@ -416,12 +432,14 @@ __secondary_data:
/*
* Setup common bits before finally enabling the MMU. Essentially
* this is just loading the page table pointer and domain access
- * registers.
+ * registers. All these registers need to be preserved by the
+ * processor setup function (or set in the case of r0)
*
* r0 = cp#15 control register
* r1 = machine ID
* r2 = atags or dtb pointer
- * r4 = page table (see ARCH_PGD_SHIFT in asm/memory.h)
+ * r4 = TTBR pointer (low word)
+ * r5 = TTBR pointer (high word if LPAE)
* r9 = processor ID
* r13 = *virtual* address to jump to upon completion
*/
@@ -440,7 +458,9 @@ __enable_mmu:
#ifdef CONFIG_CPU_ICACHE_DISABLE
bic r0, r0, #CR_I
#endif
-#ifndef CONFIG_ARM_LPAE
+#ifdef CONFIG_ARM_LPAE
+ mcrr p15, 0, r4, r5, c2 @ load TTBR0
+#else
mov r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c
new file mode 100644
index 0000000..097e2e2
--- /dev/null
+++ b/arch/arm/kernel/module-plts.c
@@ -0,0 +1,183 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <linux/elf.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cache.h>
+#include <asm/opcodes.h>
+
+#define PLT_ENT_STRIDE L1_CACHE_BYTES
+#define PLT_ENT_COUNT (PLT_ENT_STRIDE / sizeof(u32))
+#define PLT_ENT_SIZE (sizeof(struct plt_entries) / PLT_ENT_COUNT)
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define PLT_ENT_LDR __opcode_to_mem_thumb32(0xf8dff000 | \
+ (PLT_ENT_STRIDE - 4))
+#else
+#define PLT_ENT_LDR __opcode_to_mem_arm(0xe59ff000 | \
+ (PLT_ENT_STRIDE - 8))
+#endif
+
+struct plt_entries {
+ u32 ldr[PLT_ENT_COUNT];
+ u32 lit[PLT_ENT_COUNT];
+};
+
+static bool in_init(const struct module *mod, u32 addr)
+{
+ return addr - (u32)mod->module_init < mod->init_size;
+}
+
+u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val)
+{
+ struct plt_entries *plt, *plt_end;
+ int c, *count;
+
+ if (in_init(mod, loc)) {
+ plt = (void *)mod->arch.init_plt->sh_addr;
+ plt_end = (void *)plt + mod->arch.init_plt->sh_size;
+ count = &mod->arch.init_plt_count;
+ } else {
+ plt = (void *)mod->arch.core_plt->sh_addr;
+ plt_end = (void *)plt + mod->arch.core_plt->sh_size;
+ count = &mod->arch.core_plt_count;
+ }
+
+ /* Look for an existing entry pointing to 'val' */
+ for (c = *count; plt < plt_end; c -= PLT_ENT_COUNT, plt++) {
+ int i;
+
+ if (!c) {
+ /* Populate a new set of entries */
+ *plt = (struct plt_entries){
+ { [0 ... PLT_ENT_COUNT - 1] = PLT_ENT_LDR, },
+ { val, }
+ };
+ ++*count;
+ return (u32)plt->ldr;
+ }
+ for (i = 0; i < PLT_ENT_COUNT; i++) {
+ if (!plt->lit[i]) {
+ plt->lit[i] = val;
+ ++*count;
+ }
+ if (plt->lit[i] == val)
+ return (u32)&plt->ldr[i];
+ }
+ }
+ BUG();
+}
+
+static int duplicate_rel(Elf32_Addr base, const Elf32_Rel *rel, int num,
+ u32 mask)
+{
+ u32 *loc1, *loc2;
+ int i;
+
+ for (i = 0; i < num; i++) {
+ if (rel[i].r_info != rel[num].r_info)
+ continue;
+
+ /*
+ * Identical relocation types against identical symbols can
+ * still result in different PLT entries if the addend in the
+ * place is different. So resolve the target of the relocation
+ * to compare the values.
+ */
+ loc1 = (u32 *)(base + rel[i].r_offset);
+ loc2 = (u32 *)(base + rel[num].r_offset);
+ if (((*loc1 ^ *loc2) & mask) == 0)
+ return 1;
+ }
+ return 0;
+}
+
+/* Count how many PLT entries we may need */
+static unsigned int count_plts(Elf32_Addr base, const Elf32_Rel *rel, int num)
+{
+ unsigned int ret = 0;
+ int i;
+
+ /*
+ * Sure, this is order(n^2), but it's usually short, and not
+ * time critical
+ */
+ for (i = 0; i < num; i++)
+ switch (ELF32_R_TYPE(rel[i].r_info)) {
+ case R_ARM_CALL:
+ case R_ARM_PC24:
+ case R_ARM_JUMP24:
+ if (!duplicate_rel(base, rel, i,
+ __opcode_to_mem_arm(0x00ffffff)))
+ ret++;
+ break;
+#ifdef CONFIG_THUMB2_KERNEL
+ case R_ARM_THM_CALL:
+ case R_ARM_THM_JUMP24:
+ if (!duplicate_rel(base, rel, i,
+ __opcode_to_mem_thumb32(0x07ff2fff)))
+ ret++;
+#endif
+ }
+ return ret;
+}
+
+int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
+ char *secstrings, struct module *mod)
+{
+ unsigned long core_plts = 0, init_plts = 0;
+ Elf32_Shdr *s, *sechdrs_end = sechdrs + ehdr->e_shnum;
+
+ /*
+ * To store the PLTs, we expand the .text section for core module code
+ * and the .init.text section for initialization code.
+ */
+ for (s = sechdrs; s < sechdrs_end; ++s)
+ if (strcmp(".core.plt", secstrings + s->sh_name) == 0)
+ mod->arch.core_plt = s;
+ else if (strcmp(".init.plt", secstrings + s->sh_name) == 0)
+ mod->arch.init_plt = s;
+
+ if (!mod->arch.core_plt || !mod->arch.init_plt) {
+ pr_err("%s: sections missing\n", mod->name);
+ return -ENOEXEC;
+ }
+
+ for (s = sechdrs + 1; s < sechdrs_end; ++s) {
+ const Elf32_Rel *rels = (void *)ehdr + s->sh_offset;
+ int numrels = s->sh_size / sizeof(Elf32_Rel);
+ Elf32_Shdr *dstsec = sechdrs + s->sh_info;
+
+ if (s->sh_type != SHT_REL)
+ continue;
+
+ if (strstr(secstrings + s->sh_name, ".init"))
+ init_plts += count_plts(dstsec->sh_addr, rels, numrels);
+ else
+ core_plts += count_plts(dstsec->sh_addr, rels, numrels);
+ }
+
+ mod->arch.core_plt->sh_type = SHT_NOBITS;
+ mod->arch.core_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+ mod->arch.core_plt->sh_addralign = L1_CACHE_BYTES;
+ mod->arch.core_plt->sh_size = round_up(core_plts * PLT_ENT_SIZE,
+ sizeof(struct plt_entries));
+ mod->arch.core_plt_count = 0;
+
+ mod->arch.init_plt->sh_type = SHT_NOBITS;
+ mod->arch.init_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+ mod->arch.init_plt->sh_addralign = L1_CACHE_BYTES;
+ mod->arch.init_plt->sh_size = round_up(init_plts * PLT_ENT_SIZE,
+ sizeof(struct plt_entries));
+ mod->arch.init_plt_count = 0;
+ pr_debug("%s: core.plt=%x, init.plt=%x\n", __func__,
+ mod->arch.core_plt->sh_size, mod->arch.init_plt->sh_size);
+ return 0;
+}
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index af791f4..efdddcb 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -40,7 +40,12 @@
#ifdef CONFIG_MMU
void *module_alloc(unsigned long size)
{
- return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
+ void *p = __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
+ GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+ __builtin_return_address(0));
+ if (!IS_ENABLED(CONFIG_ARM_MODULE_PLTS) || p)
+ return p;
+ return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
__builtin_return_address(0));
}
@@ -110,6 +115,20 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
offset -= 0x04000000;
offset += sym->st_value - loc;
+
+ /*
+ * Route through a PLT entry if 'offset' exceeds the
+ * supported range. Note that 'offset + loc + 8'
+ * contains the absolute jump target, i.e.,
+ * @sym + addend, corrected for the +8 PC bias.
+ */
+ if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS) &&
+ (offset <= (s32)0xfe000000 ||
+ offset >= (s32)0x02000000))
+ offset = get_module_plt(module, loc,
+ offset + loc + 8)
+ - loc - 8;
+
if (offset <= (s32)0xfe000000 ||
offset >= (s32)0x02000000) {
pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
@@ -203,6 +222,17 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
offset -= 0x02000000;
offset += sym->st_value - loc;
+ /*
+ * Route through a PLT entry if 'offset' exceeds the
+ * supported range.
+ */
+ if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS) &&
+ (offset <= (s32)0xff000000 ||
+ offset >= (s32)0x01000000))
+ offset = get_module_plt(module, loc,
+ offset + loc + 4)
+ - loc - 4;
+
if (offset <= (s32)0xff000000 ||
offset >= (s32)0x01000000) {
pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
diff --git a/arch/arm/kernel/module.lds b/arch/arm/kernel/module.lds
new file mode 100644
index 0000000..3682fa1
--- /dev/null
+++ b/arch/arm/kernel/module.lds
@@ -0,0 +1,4 @@
+SECTIONS {
+ .core.plt : { BYTE(0) }
+ .init.plt : { BYTE(0) }
+}
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 91c7ba1..3b8c283 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -303,9 +303,15 @@ static int probe_current_pmu(struct arm_pmu *pmu)
static int of_pmu_irq_cfg(struct platform_device *pdev)
{
- int i;
- int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+ int i, irq;
+ int *irqs;
+ /* Don't bother with PPIs; they're already affine */
+ irq = platform_get_irq(pdev, 0);
+ if (irq >= 0 && irq_is_percpu(irq))
+ return 0;
+
+ irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
if (!irqs)
return -ENOMEM;
@@ -317,7 +323,7 @@ static int of_pmu_irq_cfg(struct platform_device *pdev)
i);
if (!dn) {
pr_warn("Failed to parse %s/interrupt-affinity[%d]\n",
- of_node_full_name(dn), i);
+ of_node_full_name(pdev->dev.of_node), i);
break;
}
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 6c777e9..e6d8c76 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -75,8 +75,7 @@ __setup("fpe=", fpe_setup);
extern void init_default_cache_policy(unsigned long);
extern void paging_init(const struct machine_desc *desc);
-extern void early_paging_init(const struct machine_desc *,
- struct proc_info_list *);
+extern void early_paging_init(const struct machine_desc *);
extern void sanity_check_meminfo(void);
extern enum reboot_mode reboot_mode;
extern void setup_dma_zone(const struct machine_desc *desc);
@@ -93,6 +92,9 @@ unsigned int __atags_pointer __initdata;
unsigned int system_rev;
EXPORT_SYMBOL(system_rev);
+const char *system_serial;
+EXPORT_SYMBOL(system_serial);
+
unsigned int system_serial_low;
EXPORT_SYMBOL(system_serial_low);
@@ -839,8 +841,25 @@ arch_initcall(customize_machine);
static int __init init_machine_late(void)
{
+ struct device_node *root;
+ int ret;
+
if (machine_desc->init_late)
machine_desc->init_late();
+
+ root = of_find_node_by_path("/");
+ if (root) {
+ ret = of_property_read_string(root, "serial-number",
+ &system_serial);
+ if (ret)
+ system_serial = NULL;
+ }
+
+ if (!system_serial)
+ system_serial = kasprintf(GFP_KERNEL, "%08x%08x",
+ system_serial_high,
+ system_serial_low);
+
return 0;
}
late_initcall(init_machine_late);
@@ -936,7 +955,9 @@ void __init setup_arch(char **cmdline_p)
parse_early_param();
- early_paging_init(mdesc, lookup_processor_type(read_cpuid_id()));
+#ifdef CONFIG_MMU
+ early_paging_init(mdesc);
+#endif
setup_dma_zone(mdesc);
sanity_check_meminfo();
arm_memblock_init(mdesc);
@@ -1109,8 +1130,7 @@ static int c_show(struct seq_file *m, void *v)
seq_printf(m, "Hardware\t: %s\n", machine_name);
seq_printf(m, "Revision\t: %04x\n", system_rev);
- seq_printf(m, "Serial\t\t: %08x%08x\n",
- system_serial_high, system_serial_low);
+ seq_printf(m, "Serial\t\t: %s\n", system_serial);
return 0;
}
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index cca5b87..90dfbed 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -86,9 +86,11 @@ void __init smp_set_ops(struct smp_operations *ops)
static unsigned long get_arch_pgd(pgd_t *pgd)
{
- phys_addr_t pgdir = virt_to_idmap(pgd);
- BUG_ON(pgdir & ARCH_PGD_MASK);
- return pgdir >> ARCH_PGD_SHIFT;
+#ifdef CONFIG_ARM_LPAE
+ return __phys_to_pfn(virt_to_phys(pgd));
+#else
+ return virt_to_phys(pgd);
+#endif
}
int __cpu_up(unsigned int cpu, struct task_struct *idle)
@@ -108,7 +110,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
#endif
#ifdef CONFIG_MMU
- secondary_data.pgdir = get_arch_pgd(idmap_pgd);
+ secondary_data.pgdir = virt_to_phys(idmap_pgd);
secondary_data.swapper_pg_dir = get_arch_pgd(swapper_pg_dir);
#endif
sync_cache_w(&secondary_data);
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
index 7a3be1d..b10e136 100644
--- a/arch/arm/kernel/tcm.c
+++ b/arch/arm/kernel/tcm.c
@@ -17,6 +17,9 @@
#include <asm/mach/map.h>
#include <asm/memory.h>
#include <asm/system_info.h>
+#include <asm/traps.h>
+
+#define TCMTR_FORMAT_MASK 0xe0000000U
static struct gen_pool *tcm_pool;
static bool dtcm_present;
@@ -176,6 +179,77 @@ static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks,
}
/*
+ * When we are running in the non-secure world and the secure world
+ * has not explicitly given us access to the TCM we will get an
+ * undefined error when reading the TCM region register in the
+ * setup_tcm_bank function (above).
+ *
+ * There are two variants of this register read that we need to trap,
+ * the read for the data TCM and the read for the instruction TCM:
+ * c0370628: ee196f11 mrc 15, 0, r6, cr9, cr1, {0}
+ * c0370674: ee196f31 mrc 15, 0, r6, cr9, cr1, {1}
+ *
+ * Our undef hook mask explicitly matches all fields of the encoded
+ * instruction other than the destination register. The mask also
+ * only allows operand 2 to have the values 0 or 1.
+ *
+ * The undefined hook is defined as __init and __initdata, and therefore
+ * must be removed before tcm_init returns.
+ *
+ * In this particular case (MRC with ARM condition code ALways) the
+ * Thumb-2 and ARM instruction encoding are identical, so this hook
+ * will work on a Thumb-2 kernel.
+ *
+ * See A8.8.107, DDI0406C_C ARM Architecture Reference Manual, Encoding
+ * T1/A1 for the bit-by-bit details.
+ *
+ * mrc p15, 0, XX, c9, c1, 0
+ * mrc p15, 0, XX, c9, c1, 1
+ * | | | | | | | +---- opc2 0|1 = 000|001
+ * | | | | | | +------- CRm 0 = 0001
+ * | | | | | +----------- CRn 0 = 1001
+ * | | | | +--------------- Rt ? = ????
+ * | | | +------------------- opc1 0 = 000
+ * | | +----------------------- coproc 15 = 1111
+ * | +-------------------------- condition ALways = 1110
+ * +----------------------------- instruction MRC = 1110
+ *
+ * Encoding this as per A8.8.107 of DDI0406C, Encoding T1/A1, yields:
+ * 1111 1111 1111 1111 0000 1111 1101 1111 Required Mask
+ * 1110 1110 0001 1001 ???? 1111 0001 0001 mrc p15, 0, XX, c9, c1, 0
+ * 1110 1110 0001 1001 ???? 1111 0011 0001 mrc p15, 0, XX, c9, c1, 1
+ * [ ] [ ] [ ]| [ ] [ ] [ ] [ ]| +--- CRm
+ * | | | | | | | | +----- SBO
+ * | | | | | | | +------- opc2
+ * | | | | | | +----------- coproc
+ * | | | | | +---------------- Rt
+ * | | | | +--------------------- CRn
+ * | | | +------------------------- SBO
+ * | | +--------------------------- opc1
+ * | +------------------------------- instruction
+ * +------------------------------------ condition
+ */
+#define TCM_REGION_READ_MASK 0xffff0fdf
+#define TCM_REGION_READ_INSTR 0xee190f11
+#define DEST_REG_SHIFT 12
+#define DEST_REG_MASK 0xf
+
+static int __init tcm_handler(struct pt_regs *regs, unsigned int instr)
+{
+ regs->uregs[(instr >> DEST_REG_SHIFT) & DEST_REG_MASK] = 0;
+ regs->ARM_pc += 4;
+ return 0;
+}
+
+static struct undef_hook tcm_hook __initdata = {
+ .instr_mask = TCM_REGION_READ_MASK,
+ .instr_val = TCM_REGION_READ_INSTR,
+ .cpsr_mask = MODE_MASK,
+ .cpsr_val = SVC_MODE,
+ .fn = tcm_handler
+};
+
+/*
* This initializes the TCM memory
*/
void __init tcm_init(void)
@@ -204,9 +278,18 @@ void __init tcm_init(void)
}
tcm_status = read_cpuid_tcmstatus();
+
+ /*
+ * This code only supports v6-compatible TCMTR implementations.
+ */
+ if (tcm_status & TCMTR_FORMAT_MASK)
+ return;
+
dtcm_banks = (tcm_status >> 16) & 0x03;
itcm_banks = (tcm_status & 0x03);
+ register_undef_hook(&tcm_hook);
+
/* Values greater than 2 for D/ITCM banks are "reserved" */
if (dtcm_banks > 2)
dtcm_banks = 0;
@@ -218,7 +301,7 @@ void __init tcm_init(void)
for (i = 0; i < dtcm_banks; i++) {
ret = setup_tcm_bank(0, i, dtcm_banks, &dtcm_end);
if (ret)
- return;
+ goto unregister;
}
/* This means you compiled more code than fits into DTCM */
if (dtcm_code_sz > (dtcm_end - DTCM_OFFSET)) {
@@ -227,6 +310,12 @@ void __init tcm_init(void)
dtcm_code_sz, (dtcm_end - DTCM_OFFSET));
goto no_dtcm;
}
+ /*
+ * This means that the DTCM sizes were 0 or the DTCM banks
+ * were inaccessible due to TrustZone configuration.
+ */
+ if (!(dtcm_end - DTCM_OFFSET))
+ goto no_dtcm;
dtcm_res.end = dtcm_end - 1;
request_resource(&iomem_resource, &dtcm_res);
dtcm_iomap[0].length = dtcm_end - DTCM_OFFSET;
@@ -250,15 +339,21 @@ no_dtcm:
for (i = 0; i < itcm_banks; i++) {
ret = setup_tcm_bank(1, i, itcm_banks, &itcm_end);
if (ret)
- return;
+ goto unregister;
}
/* This means you compiled more code than fits into ITCM */
if (itcm_code_sz > (itcm_end - ITCM_OFFSET)) {
pr_info("CPU ITCM: %u bytes of code compiled to "
"ITCM but only %lu bytes of ITCM present\n",
itcm_code_sz, (itcm_end - ITCM_OFFSET));
- return;
+ goto unregister;
}
+ /*
+ * This means that the ITCM sizes were 0 or the ITCM banks
+ * were inaccessible due to TrustZone configuration.
+ */
+ if (!(itcm_end - ITCM_OFFSET))
+ goto unregister;
itcm_res.end = itcm_end - 1;
request_resource(&iomem_resource, &itcm_res);
itcm_iomap[0].length = itcm_end - ITCM_OFFSET;
@@ -275,6 +370,9 @@ no_dtcm:
pr_info("CPU ITCM: %u bytes of code compiled to ITCM but no "
"ITCM banks present in CPU\n", itcm_code_sz);
}
+
+unregister:
+ unregister_undef_hook(&tcm_hook);
}
/*
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 3dce1a3..d358226 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -749,14 +749,6 @@ late_initcall(arm_mrc_hook_init);
#endif
-void __bad_xchg(volatile void *ptr, int size)
-{
- pr_err("xchg: bad data size: pc 0x%p, ptr 0x%p, size %d\n",
- __builtin_return_address(0), ptr, size);
- BUG();
-}
-EXPORT_SYMBOL(__bad_xchg);
-
/*
* A data abort trap was taken, but we did not handle the instruction.
* Try to abort the user program, or panic if it was the kernel.
OpenPOWER on IntegriCloud