linux/arch/arm64/include/asm/arch_gicv3.h

193 lines
4.4 KiB
C
Raw Permalink Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* arch/arm64/include/asm/arch_gicv3.h
*
* Copyright (C) 2015 ARM Ltd.
*/
#ifndef __ASM_ARCH_GICV3_H
#define __ASM_ARCH_GICV3_H
#include <asm/sysreg.h>
#ifndef __ASSEMBLY__
#include <linux/irqchip/arm-gic-common.h>
#include <linux/stringify.h>
#include <asm/barrier.h>
#include <asm/cacheflush.h>
#define read_gicreg(r) read_sysreg_s(SYS_ ## r)
#define write_gicreg(v, r) write_sysreg_s(v, SYS_ ## r)
/*
* Low-level accessors
*
* These system registers are 32 bits, but we make sure that the compiler
* sets the GP register's most significant bits to 0 with an explicit cast.
*/
static __always_inline void gic_write_dir(u32 irq)
{
write_sysreg_s(irq, SYS_ICC_DIR_EL1);
isb();
}
static inline u64 gic_read_iar_common(void)
{
u64 irqstat;
irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1);
dsb(sy);
return irqstat;
}
/*
* Cavium ThunderX erratum 23154
*
* The gicv3 of ThunderX requires a modified version for reading the
* IAR status to ensure data synchronization (access to icc_iar1_el1
* is not sync'ed before and after).
*
* Erratum 38545
*
* When a IAR register read races with a GIC interrupt RELEASE event,
* GIC-CPU interface could wrongly return a valid INTID to the CPU
* for an interrupt that is already released(non activated) instead of 0x3ff.
*
* To workaround this, return a valid interrupt ID only if there is a change
* in the active priority list after the IAR read.
*
* Common function used for both the workarounds since,
* 1. On Thunderx 88xx 1.x both erratas are applicable.
* 2. Having extra nops doesn't add any side effects for Silicons where
* erratum 23154 is not applicable.
*/
static inline u64 gic_read_iar_cavium_thunderx(void)
{
u64 irqstat, apr;
apr = read_sysreg_s(SYS_ICC_AP1R0_EL1);
nops(8);
irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1);
nops(4);
mb();
/* Max priority groups implemented is only 32 */
if (likely(apr != read_sysreg_s(SYS_ICC_AP1R0_EL1)))
return irqstat;
return 0x3ff;
}
arm64: Avoid cpus_have_const_cap() for ARM64_WORKAROUND_CAVIUM_23154 In gic_read_iar() we use cpus_have_const_cap() to check for ARM64_WORKAROUND_CAVIUM_23154 but this is not necessary and alternative_has_cap_*() would be preferable. For historical reasons, cpus_have_const_cap() is more complicated than it needs to be. Before cpucaps are finalized, it will perform a bitmap test of the system_cpucaps bitmap, and once cpucaps are finalized it will use an alternative branch. This used to be necessary to handle some race conditions in the window between cpucap detection and the subsequent patching of alternatives and static branches, where different branches could be out-of-sync with one another (or w.r.t. alternative sequences). Now that we use alternative branches instead of static branches, these are all patched atomically w.r.t. one another, and there are only a handful of cases that need special care in the window between cpucap detection and alternative patching. Due to the above, it would be nice to remove cpus_have_const_cap(), and migrate callers over to alternative_has_cap_*(), cpus_have_final_cap(), or cpus_have_cap() depending on when their requirements. This will remove redundant instructions and improve code generation, and will make it easier to determine how each callsite will behave before, during, and after alternative patching. The ARM64_WORKAROUND_CAVIUM_23154 cpucap is detected and patched early on the boot CPU before the GICv3 driver is initialized and hence before gic_read_iar() is ever called. Thus it is not necessary to use cpus_have_const_cap(), and alternative_has_cap() is equivalent. In addition, arm64's gic_read_iar() lives in irq-gic-v3.c purely for historical reasons. It was originally added prior to 32-bit arm support in commit: 6d4e11c5e2e8cd54 ("irqchip/gicv3: Workaround for Cavium ThunderX erratum 23154") When support for 32-bit arm was added, 32-bit arm's gic_read_iar() implementation was placed in <asm/arch_gicv3.h>, but the arm64 version was kept within irq-gic-v3.c as it depended on a static key local to irq-gic-v3.c and it was easier to add ifdeffery, which is what we did in commit: 7936e914f7b0827c ("irqchip/gic-v3: Refactor the arm64 specific parts") Subsequently the static key was replaced with a cpucap in commit: a4023f682739439b ("arm64: Add hypervisor safe helper for checking constant capabilities") Since that commit there has been no need to keep arm64's gic_read_iar() in irq-gic-v3.c. This patch replaces the use of cpus_have_const_cap() with alternative_has_cap_unlikely(), which will avoid generating code to test the system_cpucaps bitmap and should be better for all subsequent calls at runtime. For consistency, move the arm64-specific gic_read_iar() implementation over to arm64's <asm/arch_gicv3.h>. The ARM64_WORKAROUND_CAVIUM_23154 cpucap is added to cpucap_is_possible() so that code can be elided entirely when this is not possible. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Suzuki K Poulose <suzuki.poulose@arm.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2023-10-16 11:24:58 +01:00
static u64 __maybe_unused gic_read_iar(void)
{
if (alternative_has_cap_unlikely(ARM64_WORKAROUND_CAVIUM_23154))
return gic_read_iar_cavium_thunderx();
else
return gic_read_iar_common();
}
static inline void gic_write_ctlr(u32 val)
{
write_sysreg_s(val, SYS_ICC_CTLR_EL1);
isb();
}
static inline u32 gic_read_ctlr(void)
{
return read_sysreg_s(SYS_ICC_CTLR_EL1);
}
static inline void gic_write_grpen1(u32 val)
{
write_sysreg_s(val, SYS_ICC_IGRPEN1_EL1);
isb();
}
static inline void gic_write_sgi1r(u64 val)
{
write_sysreg_s(val, SYS_ICC_SGI1R_EL1);
}
static inline u32 gic_read_sre(void)
{
return read_sysreg_s(SYS_ICC_SRE_EL1);
}
static inline void gic_write_sre(u32 val)
{
write_sysreg_s(val, SYS_ICC_SRE_EL1);
isb();
}
static inline void gic_write_bpr1(u32 val)
{
write_sysreg_s(val, SYS_ICC_BPR1_EL1);
}
static inline u32 gic_read_pmr(void)
{
return read_sysreg_s(SYS_ICC_PMR_EL1);
}
KVM: arm64: Annotate hyp NMI-related functions as __always_inline The "inline" keyword is a hint for the compiler to inline a function. The functions system_uses_irq_prio_masking() and gic_write_pmr() are used by the code running at EL2 on a non-VHE system, so mark them as __always_inline to make sure they'll always be part of the .hyp.text section. This fixes the following splat when trying to run a VM: [ 47.625273] Kernel panic - not syncing: HYP panic: [ 47.625273] PS:a00003c9 PC:0000ca0b42049fc4 ESR:86000006 [ 47.625273] FAR:0000ca0b42049fc4 HPFAR:0000000010001000 PAR:0000000000000000 [ 47.625273] VCPU:0000000000000000 [ 47.647261] CPU: 1 PID: 217 Comm: kvm-vcpu-0 Not tainted 5.8.0-rc1-ARCH+ #61 [ 47.654508] Hardware name: Globalscale Marvell ESPRESSOBin Board (DT) [ 47.661139] Call trace: [ 47.663659] dump_backtrace+0x0/0x1cc [ 47.667413] show_stack+0x18/0x24 [ 47.670822] dump_stack+0xb8/0x108 [ 47.674312] panic+0x124/0x2f4 [ 47.677446] panic+0x0/0x2f4 [ 47.680407] SMP: stopping secondary CPUs [ 47.684439] Kernel Offset: disabled [ 47.688018] CPU features: 0x240402,20002008 [ 47.692318] Memory Limit: none [ 47.695465] ---[ end Kernel panic - not syncing: HYP panic: [ 47.695465] PS:a00003c9 PC:0000ca0b42049fc4 ESR:86000006 [ 47.695465] FAR:0000ca0b42049fc4 HPFAR:0000000010001000 PAR:0000000000000000 [ 47.695465] VCPU:0000000000000000 ]--- The instruction abort was caused by the code running at EL2 trying to fetch an instruction which wasn't mapped in the EL2 translation tables. Using objdump showed the two functions as separate symbols in the .text section. Fixes: 85738e05dc38 ("arm64: kvm: Unmask PMR before entering guest") Cc: stable@vger.kernel.org Signed-off-by: Alexandru Elisei <alexandru.elisei@arm.com> Signed-off-by: Marc Zyngier <maz@kernel.org> Acked-by: James Morse <james.morse@arm.com> Link: https://lore.kernel.org/r/20200618171254.1596055-1-alexandru.elisei@arm.com
2020-06-18 18:12:54 +01:00
static __always_inline void gic_write_pmr(u32 val)
{
write_sysreg_s(val, SYS_ICC_PMR_EL1);
}
static inline u32 gic_read_rpr(void)
{
return read_sysreg_s(SYS_ICC_RPR_EL1);
}
#define gic_read_typer(c) readq_relaxed(c)
#define gic_write_irouter(v, c) writeq_relaxed(v, c)
#define gic_read_lpir(c) readq_relaxed(c)
#define gic_write_lpir(v, c) writeq_relaxed(v, c)
#define gic_flush_dcache_to_poc(a,l) \
arm64: Rename arm64-internal cache maintenance functions Although naming across the codebase isn't that consistent, it tends to follow certain patterns. Moreover, the term "flush" isn't defined in the Arm Architecture reference manual, and might be interpreted to mean clean, invalidate, or both for a cache. Rename arm64-internal functions to make the naming internally consistent, as well as making it consistent with the Arm ARM, by specifying whether it applies to the instruction, data, or both caches, whether the operation is a clean, invalidate, or both. Also specify which point the operation applies to, i.e., to the point of unification (PoU), coherency (PoC), or persistence (PoP). This commit applies the following sed transformation to all files under arch/arm64: "s/\b__flush_cache_range\b/caches_clean_inval_pou_macro/g;"\ "s/\b__flush_icache_range\b/caches_clean_inval_pou/g;"\ "s/\binvalidate_icache_range\b/icache_inval_pou/g;"\ "s/\b__flush_dcache_area\b/dcache_clean_inval_poc/g;"\ "s/\b__inval_dcache_area\b/dcache_inval_poc/g;"\ "s/__clean_dcache_area_poc\b/dcache_clean_poc/g;"\ "s/\b__clean_dcache_area_pop\b/dcache_clean_pop/g;"\ "s/\b__clean_dcache_area_pou\b/dcache_clean_pou/g;"\ "s/\b__flush_cache_user_range\b/caches_clean_inval_user_pou/g;"\ "s/\b__flush_icache_all\b/icache_inval_all_pou/g;" Note that __clean_dcache_area_poc is deliberately missing a word boundary check at the beginning in order to match the efistub symbols in image-vars.h. Also note that, despite its name, __flush_icache_range operates on both instruction and data caches. The name change here reflects that. No functional change intended. Acked-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Fuad Tabba <tabba@google.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20210524083001.2586635-19-tabba@google.com Signed-off-by: Will Deacon <will@kernel.org>
2021-05-24 09:30:01 +01:00
dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l))
#define gits_read_baser(c) readq_relaxed(c)
#define gits_write_baser(v, c) writeq_relaxed(v, c)
#define gits_read_cbaser(c) readq_relaxed(c)
#define gits_write_cbaser(v, c) writeq_relaxed(v, c)
#define gits_write_cwriter(v, c) writeq_relaxed(v, c)
#define gicr_read_propbaser(c) readq_relaxed(c)
#define gicr_write_propbaser(v, c) writeq_relaxed(v, c)
#define gicr_write_pendbaser(v, c) writeq_relaxed(v, c)
#define gicr_read_pendbaser(c) readq_relaxed(c)
#define gicr_write_vpropbaser(v, c) writeq_relaxed(v, c)
#define gicr_read_vpropbaser(c) readq_relaxed(c)
#define gicr_write_vpendbaser(v, c) writeq_relaxed(v, c)
#define gicr_read_vpendbaser(c) readq_relaxed(c)
static inline bool gic_prio_masking_enabled(void)
{
return system_uses_irq_prio_masking();
}
static inline void gic_pmr_mask_irqs(void)
{
gic_write_pmr(GIC_PRIO_IRQOFF);
}
static inline void gic_arch_enable_irqs(void)
{
asm volatile ("msr daifclr, #3" : : : "memory");
}
arm64: add ARM64_HAS_GIC_PRIO_RELAXED_SYNC cpucap When Priority Mask Hint Enable (PMHE) == 0b1, the GIC may use the PMR value to determine whether to signal an IRQ to a PE, and consequently after a change to the PMR value, a DSB SY may be required to ensure that interrupts are signalled to a CPU in finite time. When PMHE == 0b0, interrupts are always signalled to the relevant PE, and all masking occurs locally, without requiring a DSB SY. Since commit: f226650494c6aa87 ("arm64: Relax ICC_PMR_EL1 accesses when ICC_CTLR_EL1.PMHE is clear") ... we handle this dynamically: in most cases a static key is used to determine whether to issue a DSB SY, but the entry code must read from ICC_CTLR_EL1 as static keys aren't accessible from plain assembly. It would be much nicer to use an alternative instruction sequence for the DSB, as this would avoid the need to read from ICC_CTLR_EL1 in the entry code, and for most other code this will result in simpler code generation with fewer instructions and fewer branches. This patch adds a new ARM64_HAS_GIC_PRIO_RELAXED_SYNC cpucap which is only set when ICC_CTLR_EL1.PMHE == 0b0 (and GIC priority masking is in use). This allows us to replace the existing users of the `gic_pmr_sync` static key with alternative sequences which default to a DSB SY and are relaxed to a NOP when PMHE is not in use. The entry assembly management of the PMR is slightly restructured to use a branch (rather than multiple NOPs) when priority masking is not in use. This is more in keeping with other alternatives in the entry assembly, and permits the use of a separate alternatives for the PMHE-dependent DSB SY (and removal of the conditional branch this currently requires). For consistency I've adjusted both the save and restore paths. According to bloat-o-meter, when building defconfig + CONFIG_ARM64_PSEUDO_NMI=y this shrinks the kernel text by ~4KiB: | add/remove: 4/2 grow/shrink: 42/310 up/down: 332/-5032 (-4700) The resulting vmlinux is ~66KiB smaller, though the resulting Image size is unchanged due to padding and alignment: | [mark@lakrids:~/src/linux]% ls -al vmlinux-* | -rwxr-xr-x 1 mark mark 137508344 Jan 17 14:11 vmlinux-after | -rwxr-xr-x 1 mark mark 137575440 Jan 17 13:49 vmlinux-before | [mark@lakrids:~/src/linux]% ls -al Image-* | -rw-r--r-- 1 mark mark 38777344 Jan 17 14:11 Image-after | -rw-r--r-- 1 mark mark 38777344 Jan 17 13:49 Image-before Prior to this patch we did not verify the state of ICC_CTLR_EL1.PMHE on secondary CPUs. As of this patch this is verified by the cpufeature code when using GIC priority masking (i.e. when using pseudo-NMIs). Note that since commit: 7e3a57fa6ca831fa ("arm64: Document ICC_CTLR_EL3.PMHE setting requirements") ... Documentation/arm64/booting.rst specifies: | - ICC_CTLR_EL3.PMHE (bit 6) must be set to the same value across | all CPUs the kernel is executing on, and must stay constant | for the lifetime of the kernel. ... so that should not adversely affect any compliant systems, and as we'll only check for the absense of PMHE when using pseudo-NMIs, this will only fire when such mismatch will adversely affect the system. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Marc Zyngier <maz@kernel.org> Cc: Mark Brown <broonie@kernel.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20230130145429.903791-5-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2023-01-30 14:54:28 +00:00
static inline bool gic_has_relaxed_pmr_sync(void)
{
return cpus_have_cap(ARM64_HAS_GIC_PRIO_RELAXED_SYNC);
}
#endif /* __ASSEMBLY__ */
#endif /* __ASM_ARCH_GICV3_H */