@@ -490,6 +490,21 @@ config FORCE_MAX_ZONEORDER
default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
default "11"
+config USE_ICC_SYSREGS_FOR_IRQFLAGS
+ bool "Use ICC system registers for IRQ masking"
+ select CONFIG_ARM_GIC_V3
+ help
+ Using the ICC system registers for IRQ masking makes it possible
+ to simulate NMI on ARM64 systems. This allows several interesting
+ features (especially debug features) to be used on these systems.
+
+ Say Y here to implement IRQ masking using ICC system
+ registers. This will result in an unbootable kernel if these
+ registers are not implemented or made inaccessible by the
+ EL3 firmare or EL2 hypervisor (if present).
+
+ If unsure, say N
+
menuconfig ARMV8_DEPRECATED
bool "Emulate deprecated/obsolete ARMv8 instructions"
depends on COMPAT
@@ -23,6 +23,9 @@
#ifndef __ASM_ASSEMBLER_H
#define __ASM_ASSEMBLER_H
+#include <linux/irqchip/arm-gic-v3.h>
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
#include <asm/ptrace.h>
#include <asm/thread_info.h>
@@ -41,12 +44,30 @@
/*
* Enable and disable interrupts.
*/
- .macro disable_irq
+ .macro disable_irq, tmp
+#ifdef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
+ mov \tmp, #ICC_PMR_EL1_MASKED
+alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
msr daifset, #2
+alternative_else
+ msr_s ICC_PMR_EL1, \tmp
+alternative_endif
+#else
+ msr daifset, #2
+#endif
.endm
- .macro enable_irq
+ .macro enable_irq, tmp
+#ifdef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
+ mov \tmp, #ICC_PMR_EL1_UNMASKED
+alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
+ msr daifclr, #2
+alternative_else
+ msr_s ICC_PMR_EL1, \tmp
+alternative_endif
+#else
msr daifclr, #2
+#endif
.endm
/*
@@ -78,13 +99,19 @@
9990:
.endm
+
/*
* Enable both debug exceptions and interrupts. This is likely to be
* faster than two daifclr operations, since writes to this register
* are self-synchronising.
*/
- .macro enable_dbg_and_irq
+ .macro enable_dbg_and_irq, tmp
+#ifdef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
+ enable_dbg
+ enable_irq \tmp
+#else
msr daifclr, #(8 | 2)
+#endif
.endm
/*
@@ -18,8 +18,14 @@
#ifdef __KERNEL__
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
#include <asm/ptrace.h>
+#ifndef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
+
/*
* CPU interrupt mask handling.
*/
@@ -84,6 +90,107 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
return flags & PSR_I_BIT;
}
+static inline void maybe_switch_to_sysreg_gic_cpuif(void) {}
+
+#else /* CONFIG_IRQFLAGS_GIC_MASKING */
+
+/*
+ * CPU interrupt mask handling.
+ */
+static inline unsigned long arch_local_irq_save(void)
+{
+ unsigned long flags, masked = ICC_PMR_EL1_MASKED;
+
+ asm volatile(ALTERNATIVE(
+ "mrs %0, daif // arch_local_irq_save\n"
+ "msr daifset, #2",
+ /* --- */
+ "mrs_s %0, " __stringify(ICC_PMR_EL1) "\n"
+ "msr_s " __stringify(ICC_PMR_EL1) ",%1",
+ ARM64_HAS_SYSREG_GIC_CPUIF)
+ : "=&r" (flags)
+ : "r" (masked)
+ : "memory");
+
+ return flags;
+}
+
+static inline void arch_local_irq_enable(void)
+{
+ unsigned long unmasked = ICC_PMR_EL1_UNMASKED;
+
+ asm volatile(ALTERNATIVE(
+ "msr daifclr, #2 // arch_local_irq_enable",
+ "msr_s " __stringify(ICC_PMR_EL1) ",%0",
+ ARM64_HAS_SYSREG_GIC_CPUIF)
+ :
+ : "r" (unmasked)
+ : "memory");
+}
+
+static inline void arch_local_irq_disable(void)
+{
+ unsigned long masked = ICC_PMR_EL1_MASKED;
+
+ asm volatile(ALTERNATIVE(
+ "msr daifset, #2 // arch_local_irq_disable",
+ "msr_s " __stringify(ICC_PMR_EL1) ",%0",
+ ARM64_HAS_SYSREG_GIC_CPUIF)
+ :
+ : "r" (masked)
+ : "memory");
+}
+
+/*
+ * Save the current interrupt enable state.
+ */
+static inline unsigned long arch_local_save_flags(void)
+{
+ unsigned long flags;
+
+ asm volatile(ALTERNATIVE(
+ "mrs %0, daif // arch_local_save_flags",
+ "mrs_s %0, " __stringify(ICC_PMR_EL1),
+ ARM64_HAS_SYSREG_GIC_CPUIF)
+ : "=r" (flags)
+ :
+ : "memory");
+
+ return flags;
+}
+
+/*
+ * restore saved IRQ state
+ */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+ asm volatile(ALTERNATIVE(
+ "msr daif, %0 // arch_local_irq_restore",
+ "msr_s " __stringify(ICC_PMR_EL1) ",%0",
+ ARM64_HAS_SYSREG_GIC_CPUIF)
+ :
+ : "r" (flags)
+ : "memory");
+}
+
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+ asm volatile(ALTERNATIVE(
+ "and %0, %0, #" __stringify(PSR_I_BIT) "\n"
+ "nop",
+ /* --- */
+ "and %0, %0, # " __stringify(ICC_PMR_EL1_G_BIT) "\n"
+ "eor %0, %0, # " __stringify(ICC_PMR_EL1_G_BIT),
+ ARM64_HAS_SYSREG_GIC_CPUIF)
+ : "+r" (flags));
+
+ return flags;
+}
+
+void maybe_switch_to_sysreg_gic_cpuif(void);
+
+#endif /* CONFIG_IRQFLAGS_GIC_MASKING */
+
#define local_fiq_enable() asm("msr daifclr, #1" : : : "memory")
#define local_fiq_disable() asm("msr daifset, #1" : : : "memory")
@@ -25,6 +25,24 @@
#define CurrentEL_EL1 (1 << 2)
#define CurrentEL_EL2 (2 << 2)
+/* PMR values used to mask/unmask interrupts */
+#define ICC_PMR_EL1_G_SHIFT 6
+#define ICC_PMR_EL1_G_BIT (1 << ICC_PMR_EL1_G_SHIFT)
+#define ICC_PMR_EL1_UNMASKED 0xf0
+#define ICC_PMR_EL1_MASKED (ICC_PMR_EL1_UNMASKED ^ ICC_PMR_EL1_G_BIT)
+
+/*
+ * This is the GIC interrupt mask bit. It is not actually part of the
+ * PSR and so does not appear in the user API, we are simply using some
+ * reserved bits in the PSR to store some state from the interrupt
+ * controller. The context save/restore functions will extract the
+ * ICC_PMR_EL1_G_BIT and save it as the PSR_G_BIT.
+ */
+#define PSR_G_BIT 0x00400000
+#define PSR_G_SHIFT 22
+#define PSR_G_PMR_G_SHIFT (PSR_G_SHIFT - ICC_PMR_EL1_G_SHIFT)
+#define PSR_I_PMR_G_SHIFT (7 - ICC_PMR_EL1_G_SHIFT)
+
/* AArch32-specific ptrace requests */
#define COMPAT_PTRACE_GETREGS 12
#define COMPAT_PTRACE_SETREGS 13
@@ -20,6 +20,7 @@
#include <linux/init.h>
#include <linux/linkage.h>
+#include <linux/irqchip/arm-gic-v3.h>
#include <asm/alternative.h>
#include <asm/assembler.h>
@@ -96,6 +97,26 @@
.endif
mrs x22, elr_el1
mrs x23, spsr_el1
+#ifdef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
+ /*
+ * Save the context held in the PMR register and copy the current
+ * I bit state to the PMR. Re-enable of the I bit happens in later
+ * code that knows what type of trap we are handling.
+ */
+alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
+ b 1f
+alternative_else
+ mrs_s x20, ICC_PMR_EL1 // Get PMR
+alternative_endif
+ and x20, x20, #ICC_PMR_EL1_G_BIT // Extract mask bit
+ lsl x20, x20, #PSR_G_PMR_G_SHIFT // Shift to a PSTATE RES0 bit
+ eor x20, x20, #PSR_G_BIT // Invert bit
+ orr x23, x20, x23 // Store PMR within PSTATE
+ mov x20, #ICC_PMR_EL1_MASKED
+ msr_s ICC_PMR_EL1, x20 // Mask normal interrupts at PMR
+1:
+#endif
+
stp lr, x21, [sp, #S_LR]
stp x22, x23, [sp, #S_PC]
@@ -141,6 +162,22 @@ alternative_else
alternative_endif
#endif
.endif
+#ifdef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
+ /*
+ * Restore the context to the PMR (and ensure the reserved bit is
+ * restored to zero before being copied back to the PSR).
+ */
+alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
+ b 1f
+alternative_else
+ and x20, x22, #PSR_G_BIT // Get stolen PSTATE bit
+alternative_endif
+ and x22, x22, #~PSR_G_BIT // Clear stolen bit
+ lsr x20, x20, #PSR_G_PMR_G_SHIFT // Shift back to PMR mask
+ eor x20, x20, #ICC_PMR_EL1_UNMASKED // x20 gets 0xf0 or 0xb0
+ msr_s ICC_PMR_EL1, x20 // Write to PMR
+1:
+#endif
msr elr_el1, x21 // set up the return data
msr spsr_el1, x22
ldp x0, x1, [sp, #16 * 0]
@@ -306,14 +343,30 @@ el1_da:
mrs x0, far_el1
enable_dbg
// re-enable interrupts if they were enabled in the aborted context
+#ifdef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
+alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
tbnz x23, #7, 1f // PSR_I_BIT
- enable_irq
+ nop
+ nop
+ msr daifclr, #2
+1:
+alternative_else
+ tbnz x23, #PSR_G_SHIFT, 1f // PSR_G_BIT
+ mov x2, #ICC_PMR_EL1_UNMASKED
+ msr_s ICC_PMR_EL1, x2
+ msr daifclr, #2
1:
+alternative_endif
+#else
+ tbnz x23, #7, 1f // PSR_I_BIT
+ enable_irq x2
+1:
+#endif
mov x2, sp // struct pt_regs
bl do_mem_abort
// disable interrupts before pulling preserved data off the stack
- disable_irq
+ disable_irq x21
kernel_exit 1
el1_sp_pc:
/*
@@ -466,7 +519,7 @@ el0_da:
*/
mrs x26, far_el1
// enable interrupts before calling the main handler
- enable_dbg_and_irq
+ enable_dbg_and_irq x0
ct_user_exit
bic x0, x26, #(0xff << 56)
mov x1, x25
@@ -479,7 +532,7 @@ el0_ia:
*/
mrs x26, far_el1
// enable interrupts before calling the main handler
- enable_dbg_and_irq
+ enable_dbg_and_irq x0
ct_user_exit
mov x0, x26
orr x1, x25, #1 << 24 // use reserved ISS bit for instruction aborts
@@ -512,7 +565,7 @@ el0_sp_pc:
*/
mrs x26, far_el1
// enable interrupts before calling the main handler
- enable_dbg_and_irq
+ enable_dbg_and_irq x0
ct_user_exit
mov x0, x26
mov x1, x25
@@ -524,7 +577,7 @@ el0_undef:
* Undefined instruction
*/
// enable interrupts before calling the main handler
- enable_dbg_and_irq
+ enable_dbg_and_irq x0
ct_user_exit
mov x0, sp
bl do_undefinstr
@@ -605,7 +658,7 @@ ENDPROC(cpu_switch_to)
* and this includes saving x0 back into the kernel stack.
*/
ret_fast_syscall:
- disable_irq // disable interrupts
+ disable_irq x21 // disable interrupts
str x0, [sp, #S_X0] // returned x0
ldr x1, [tsk, #TI_FLAGS] // re-check for syscall tracing
and x2, x1, #_TIF_SYSCALL_WORK
@@ -615,7 +668,7 @@ ret_fast_syscall:
enable_step_tsk x1, x2
kernel_exit 0
ret_fast_syscall_trace:
- enable_irq // enable interrupts
+ enable_irq x0 // enable interrupts
b __sys_trace_return_skipped // we already saved x0
/*
@@ -628,7 +681,7 @@ work_pending:
mov x0, sp // 'regs'
tst x2, #PSR_MODE_MASK // user mode regs?
b.ne no_work_pending // returning to kernel
- enable_irq // enable interrupts for do_notify_resume()
+ enable_irq x21 // enable interrupts for do_notify_resume()
bl do_notify_resume
b ret_to_user
work_resched:
@@ -638,7 +691,7 @@ work_resched:
* "slow" syscall return path.
*/
ret_to_user:
- disable_irq // disable interrupts
+ disable_irq x21 // disable interrupts
ldr x1, [tsk, #TI_FLAGS]
and x2, x1, #_TIF_WORK_MASK
cbnz x2, work_pending
@@ -669,7 +722,7 @@ el0_svc:
mov sc_nr, #__NR_syscalls
el0_svc_naked: // compat entry point
stp x0, scno, [sp, #S_ORIG_X0] // save the original x0 and syscall number
- enable_dbg_and_irq
+ enable_dbg_and_irq x16
ct_user_exit 1
ldr x16, [tsk, #TI_FLAGS] // check for syscall hooks
@@ -427,6 +427,38 @@ __create_page_tables:
ENDPROC(__create_page_tables)
.ltorg
+#ifdef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
+/*
+ * void maybe_switch_to_sysreg_gic_cpuif(void)
+ *
+ * Enable interrupt controller system register access if this feature
+ * has been detected by the alternatives system.
+ *
+ * Before we jump into generic code we must enable interrupt controller system
+ * register access because this is required by the irqflags macros. We must
+ * also mask interrupts at the PMR and unmask them within the PSR. That leaves
+ * us set up and ready for the kernel to make its first call to
+ * arch_local_irq_enable().
+
+ *
+ */
+ENTRY(maybe_switch_to_sysreg_gic_cpuif)
+alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
+ b 1f
+alternative_else
+ mrs_s x0, ICC_SRE_EL1
+alternative_endif
+ orr x0, x0, #1
+ msr_s ICC_SRE_EL1, x0 // Set ICC_SRE_EL1.SRE==1
+ isb // Make sure SRE is now set
+ mov x0, ICC_PMR_EL1_MASKED
+ msr_s ICC_PMR_EL1, x0 // Prepare for unmask of I bit
+ msr daifclr, #2 // Clear the I bit
+1:
+ ret
+ENDPROC(maybe_switch_to_sysreg_gic_cpuif)
+#endif
+
/*
* The following fragment of code is executed with the MMU enabled.
*/
@@ -613,6 +645,9 @@ ENDPROC(secondary_startup)
ENTRY(__secondary_switched)
ldr x0, [x21] // get secondary_data.stack
mov sp, x0
+#ifdef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
+ bl maybe_switch_to_sysreg_gic_cpuif
+#endif
mov x29, #0
b secondary_start_kernel
ENDPROC(__secondary_switched)
@@ -218,6 +218,12 @@ static void __init setup_processor(void)
apply_alternatives_early();
/*
+ * Conditionally switch to GIC PMR for interrupt masking
+ * (this will be a nop if we are using normal interrupt masking)
+ */
+ maybe_switch_to_sysreg_gic_cpuif();
+
+ /*
* Check for sane CTR_EL0.CWG value.
*/
cwg = cache_type_cwg();
@@ -20,6 +20,7 @@
#include <linux/init.h>
#include <linux/linkage.h>
+#include <linux/irqchip/arm-gic-v3.h>
#include <asm/assembler.h>
#include <asm/asm-offsets.h>
#include <asm/hwcap.h>
@@ -45,11 +46,33 @@
* cpu_do_idle()
*
* Idle the processor (wait for interrupt).
+ *
+ * If CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS is set we must do additional
+ * work to ensure that interrupts are not masked at the PMR (because the
+ * core will not wake up if we block the wake up signal in the interrupt
+ * controller).
*/
ENTRY(cpu_do_idle)
+#ifdef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
+alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF
+#endif
+ dsb sy // WFI may enter a low-power mode
+ wfi
+ ret
+#ifdef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
+alternative_else
+ mrs x0, daif // save I bit
+ msr daifset, #2 // set I bit
+ mrs_s x1, ICC_PMR_EL1 // save PMR
+alternative_endif
+ mov x2, #ICC_PMR_EL1_UNMASKED
+ msr_s ICC_PMR_EL1, x2 // unmask at PMR
dsb sy // WFI may enter a low-power mode
wfi
+ msr_s ICC_PMR_EL1, x1 // restore PMR
+ msr daif, x0 // restore I bit
ret
+#endif
ENDPROC(cpu_do_idle)
#ifdef CONFIG_CPU_PM
@@ -35,6 +35,12 @@
#include "irq-gic-common.h"
+/*
+ * Copied from arm-gic.h (which we cannot include here because it conflicts
+ * with arm-gic-v3.h)
+ */
+#define GIC_DIST_PRI 0x400
+
struct redist_region {
void __iomem *redist_base;
phys_addr_t phys_base;
@@ -117,8 +123,33 @@ static void gic_redist_wait_for_rwp(void)
static u64 __maybe_unused gic_read_iar(void)
{
u64 irqstat;
+ u64 __maybe_unused daif;
+ u64 __maybe_unused pmr;
+ u64 __maybe_unused default_pmr_value = DEFAULT_PMR_VALUE;
+#ifndef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+#else
+ /*
+ * The PMR may be configured to mask interrupts when this code is
+ * called, thus in order to acknowledge interrupts we must set the
+ * PMR to its default value before reading from the IAR.
+ *
+ * To do this without taking an interrupt we also ensure the I bit
+ * is set whilst we are interfering with the value of the PMR.
+ */
+ asm volatile(
+ "mrs %1, daif\n" /* save I bit */
+ "msr daifset, #2\n" /* set I bit */
+ "mrs_s %2, " __stringify(ICC_PMR_EL1) "\n" /* save PMR */
+ "msr_s " __stringify(ICC_PMR_EL1) ",%3\n" /* set PMR */
+ "mrs_s %0, " __stringify(ICC_IAR1_EL1) "\n" /* ack int */
+ "msr_s " __stringify(ICC_PMR_EL1) ",%2\n" /* restore PMR */
+ "isb\n"
+ "msr daif, %1" /* restore I */
+ : "=r" (irqstat), "=&r" (daif), "=&r" (pmr)
+ : "r" (default_pmr_value));
+#endif
return irqstat;
}
@@ -149,7 +180,7 @@ static void __maybe_unused gic_write_sgi1r(u64 val)
asm volatile("msr_s " __stringify(ICC_SGI1R_EL1) ", %0" : : "r" (val));
}
-static void gic_enable_sre(void)
+static void __maybe_unused gic_enable_sre(void)
{
u64 val;
@@ -500,11 +531,13 @@ static int gic_populate_rdist(void)
static void gic_cpu_sys_reg_init(void)
{
+#ifndef CONFIG_USE_ICC_SYSREGS_FOR_IRQFLAGS
/* Enable system registers */
gic_enable_sre();
/* Set priority mask register */
gic_write_pmr(DEFAULT_PMR_VALUE);
+#endif
/*
* Some firmwares hand over to the kernel with the BPR changed from
@@ -18,6 +18,7 @@
#ifndef __LINUX_IRQCHIP_ARM_GIC_V3_H
#define __LINUX_IRQCHIP_ARM_GIC_V3_H
+#include <asm/barrier.h>
#include <asm/sysreg.h>
/*
@@ -371,6 +372,13 @@
#include <asm/msi.h>
/*
+ * This header is included from a lot of critical places (including
+ * from asm/irqflags.h). We must forward declare a few bits and pieces
+ * needed later in this file to avoid header loops.
+ */
+struct device_node;
+
+/*
* We need a value to serve as a irq-type for LPIs. Choose one that will
* hopefully pique the interest of the reviewer.
*/
@@ -53,7 +53,7 @@
#define GICD_INT_EN_CLR_X32 0xffffffff
#define GICD_INT_EN_SET_SGI 0x0000ffff
#define GICD_INT_EN_CLR_PPI 0xffff0000
-#define GICD_INT_DEF_PRI 0xa0
+#define GICD_INT_DEF_PRI 0xc0
#define GICD_INT_DEF_PRI_X4 ((GICD_INT_DEF_PRI << 24) |\
(GICD_INT_DEF_PRI << 16) |\
(GICD_INT_DEF_PRI << 8) |\
Currently irqflags is implemented using the PSR's I bit. It is possible to implement irqflags by using the co-processor interface to the GIC. Using the co-processor interface makes it feasible to simulate NMIs using GIC interrupt prioritization. This patch changes the irqflags macros to modify, save and restore ICC_PMR_EL1. This has a substantial knock on effect for the rest of the kernel. There are four reasons for this: 1. The state of the ICC_PMR_EL1_G_BIT becomes part of the CPU context and must be saved and restored during traps. To simplify the additional context management the ICC_PMR_EL1_G_BIT is converted into a fake (reserved) bit within the PSR (PSR_G_BIT). Naturally this approach will need to be changed if future ARM architecture extensions make use of this bit. 2. The hardware automatically masks the I bit (at boot, during traps, etc). When the I bit is set by hardware we must add code to switch from I bit masking and PMR masking. 3. Some instructions, noteably wfi, require that the PMR not be used for interrupt masking. Before calling these instructions we must switch from PMR masking to I bit masking. 4. We use the alternatives system to all a single kernel to boot and switch between the different masking approaches. Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org> --- arch/arm64/Kconfig | 15 ++++++ arch/arm64/include/asm/assembler.h | 33 ++++++++++-- arch/arm64/include/asm/irqflags.h | 107 +++++++++++++++++++++++++++++++++++++ arch/arm64/include/asm/ptrace.h | 18 +++++++ arch/arm64/kernel/entry.S | 75 ++++++++++++++++++++++---- arch/arm64/kernel/head.S | 35 ++++++++++++ arch/arm64/kernel/setup.c | 6 +++ arch/arm64/mm/proc.S | 23 ++++++++ drivers/irqchip/irq-gic-v3.c | 35 +++++++++++- include/linux/irqchip/arm-gic-v3.h | 8 +++ include/linux/irqchip/arm-gic.h | 2 +- 11 files changed, 341 insertions(+), 16 deletions(-)