* [PATCH v14 01/15] xen/arm: Add suspend and resume timer helpers
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
@ 2026-11-17 1:04 ` Mykola Kvach
2026-11-17 1:04 ` [PATCH v14 02/15] xen/arm: gic-v2: Implement GIC suspend/resume functions Mykola Kvach
` (13 subsequent siblings)
14 siblings, 0 replies; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:04 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk, Julien Grall, Luca Fancellu
From: Mirela Simonovic <mirela.simonovic@aggios.com>
Timer interrupts must be disabled while the system is suspended to prevent
spurious wake-ups. Suspending timers in Xen consists of disabling the
physical timer and the hypervisor timer on the current CPU. The virtual
timer does not need explicit handling here, as it is already disabled on
vCPU context switch and its state is restored per-vCPU on the next context
restore.
Resuming consists of raising TIMER_SOFTIRQ, which prompts the generic
timer code to reprogram the hypervisor timer with the correct timeout.
Xen does not use or expose the physical timer, so it remains disabled
across suspend/resume.
Introduce a new helper, disable_phys_hyp_timers(), to encapsulate disabling
of the physical and hypervisor timers.
Signed-off-by: Mirela Simonovic <mirela.simonovic@aggios.com>
Signed-off-by: Saeed Nowshadi <saeed.nowshadi@xilinx.com>
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Acked-by: Julien Grall <jgrall@amazon.com>
Reviewed-by: Luca Fancellu <luca.fancellu@arm.com>
---
Changes in V7:
- Dropped EL1/EL2 wording; use "physical timer" and "hypervisor timer"
- Renamed helper to disable_phys_hyp_timers() to reflect its actual scope
- Clarified virtual timer handling (disabled on vCPU switch-out, restored
on context restore) and added comments in suspend/resume paths
- Added resume comment explaining which timers are restored by
TIMER_SOFTIRQ
---
xen/arch/arm/include/asm/time.h | 5 ++++
xen/arch/arm/time.c | 44 ++++++++++++++++++++++++++++-----
2 files changed, 43 insertions(+), 6 deletions(-)
diff --git a/xen/arch/arm/include/asm/time.h b/xen/arch/arm/include/asm/time.h
index fd79dd31eb..7ffa0b5ac9 100644
--- a/xen/arch/arm/include/asm/time.h
+++ b/xen/arch/arm/include/asm/time.h
@@ -106,6 +106,11 @@ void preinit_xen_time(void);
void force_update_vcpu_system_time(struct vcpu *v);
+#ifdef CONFIG_SYSTEM_SUSPEND
+void time_suspend(void);
+void time_resume(void);
+#endif /* CONFIG_SYSTEM_SUSPEND */
+
#endif /* __ARM_TIME_H__ */
/*
* Local variables:
diff --git a/xen/arch/arm/time.c b/xen/arch/arm/time.c
index 295afa685a..edd41b6e31 100644
--- a/xen/arch/arm/time.c
+++ b/xen/arch/arm/time.c
@@ -311,6 +311,14 @@ static void check_timer_irq_cfg(unsigned int irq, const char *which)
static DEFINE_PER_CPU_READ_MOSTLY(struct irqaction, irq_hyp);
static DEFINE_PER_CPU_READ_MOSTLY(struct irqaction, irq_virt);
+/* Disable physical and hypervisor timers on the current CPU */
+static inline void disable_phys_hyp_timers(void)
+{
+ WRITE_SYSREG(0, CNTP_CTL_EL0); /* Physical timer disabled */
+ WRITE_SYSREG(0, CNTHP_CTL_EL2); /* Hypervisor's timer disabled */
+ isb();
+}
+
/* Set up the timer interrupt on this CPU */
void init_timer_interrupt(void)
{
@@ -321,9 +329,7 @@ void init_timer_interrupt(void)
WRITE_SYSREG64(0, CNTVOFF_EL2); /* No VM-specific offset */
/* Do not let the VMs program the physical timer, only read the physical counter */
WRITE_SYSREG(CNTHCTL_EL2_EL1PCTEN, CNTHCTL_EL2);
- WRITE_SYSREG(0, CNTP_CTL_EL0); /* Physical timer disabled */
- WRITE_SYSREG(0, CNTHP_CTL_EL2); /* Hypervisor's timer disabled */
- isb();
+ disable_phys_hyp_timers();
hyp_action->name = "hyptimer";
hyp_action->handler = htimer_interrupt;
@@ -348,9 +354,7 @@ void init_timer_interrupt(void)
*/
static void deinit_timer_interrupt(void)
{
- WRITE_SYSREG(0, CNTP_CTL_EL0); /* Disable physical timer */
- WRITE_SYSREG(0, CNTHP_CTL_EL2); /* Disable hypervisor's timer */
- isb();
+ disable_phys_hyp_timers();
release_irq(timer_irq[TIMER_HYP_PPI], NULL);
release_irq(timer_irq[TIMER_VIRT_PPI], NULL);
@@ -390,6 +394,34 @@ void domain_set_time_offset(struct domain *d, int64_t time_offset_seconds)
/* XXX update guest visible wallclock time */
}
+#ifdef CONFIG_SYSTEM_SUSPEND
+
+void time_suspend(void)
+{
+ /* CNTV already disabled by virt_timer_save() during vcpu context switch. */
+ disable_phys_hyp_timers();
+}
+
+void time_resume(void)
+{
+ /*
+ * Raising TIMER_SOFTIRQ triggers generic timer code to reprogram the
+ * hypervisor timer with the correct timeout (not known here).
+ *
+ * Xen doesn't use or expose the physical timer, so it remains disabled
+ * across suspend/resume.
+ *
+ * The virtual timer state is restored per-vCPU on the next context switch.
+ *
+ * No further action is needed to restore timekeeping after power down,
+ * since the system counter is unaffected. See ARM DDI 0487 L.a, D12.1.2
+ * "The system counter must be implemented in an always-on power domain."
+ */
+ raise_softirq(TIMER_SOFTIRQ);
+}
+
+#endif /* CONFIG_SYSTEM_SUSPEND */
+
static int cpu_time_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v14 02/15] xen/arm: gic-v2: Implement GIC suspend/resume functions
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
2026-11-17 1:04 ` [PATCH v14 01/15] xen/arm: Add suspend and resume timer helpers Mykola Kvach
@ 2026-11-17 1:04 ` Mykola Kvach
2026-11-17 1:04 ` [PATCH v14 03/15] xen/arm: gic-v3: tolerate retained redistributor LPI state across CPU_OFF Mykola Kvach
` (12 subsequent siblings)
14 siblings, 0 replies; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:04 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk
From: Mirela Simonovic <mirela.simonovic@aggios.com>
System suspend may lead to a state where GIC would be powered down.
Therefore, Xen should save/restore the context of GIC on suspend/resume.
Note that the context consists of states of registers which are
controlled by the hypervisor. Other GIC registers which are accessible
by guests are saved/restored on context switch.
Do not save or restore physical pending interrupt state, including
SGIs and PPI/SPI pending bits in GICD_ISPENDR. Before this point, device
drivers must stop normal I/O and quiesce non-wakeup interrupt sources.
Earlier events must have been handled or remain recorded outside the
GIC. The platform must preserve wakeup events throughout suspend entry
and sleep if the GIC loses state. Level sources still asserted after
resume become pending again. Edge events need state retained outside
the GIC; saving GICD_ISPENDR would not cover events arriving after the
read.
Keep the Distributor and CPU interface control state unchanged during
suspend entry. GICv2 wakeup signals depend on Distributor group enables,
and firmware may check pending interrupts through the CPU interface
before accepting SYSTEM_SUSPEND. Leave shutdown and wakeup setup to
firmware. Disable the interfaces while restoring their state on resume.
CPU-interface active-priority state is not restored. Xen enters this
path with local IRQs disabled and must have no active-priority context
to replay after resume. If any visible GICC_APRn bit is still set,
abort suspend with -EBUSY without changing the GIC control registers.
This does not apply to distributor active state. With GICv2 EOImode==1,
EOIR only drops the interrupt priority; final deactivation is a separate
step. For guest-routed interrupts, Xen can have already EOIed the physical
IRQ while deactivation is still pending on the vGIC/GICV path. Therefore
GICD_ISACTIVER is preserved as architectural in-flight interrupt state.
Signed-off-by: Mirela Simonovic <mirela.simonovic@aggios.com>
Signed-off-by: Saeed Nowshadi <saeed.nowshadi@xilinx.com>
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
---
Changes in V13:
- Use size_t for GICD word-access offsets to match the suspend code (MISRA
Rule 10.3). No functional change.
- Cast the APR mask to uint32_t; it contains at most 32 bits (MISRA Rule
10.3). No functional change.
- Leave the CPU interface and Distributor control state unchanged during
suspend entry, including when the active-priority check fails.
- Explain why pending interrupt state is not saved and document the
device and platform requirements for preserving events.
Changes in V10:
- Limit GICC_APR<n> active-priority checks to APR bits visible from
the Xen CPU-interface view.
- Avoid touching reserved GICD_IPRIORITYR/GICD_ITARGETSR words when the
last implemented interrupt block is partial.
- Restore distributor configuration before restoring interrupt enable
state, so GICD_ICFGR is written while the corresponding interrupts are
disabled.
Changes in V9:
- Skip saving/restoring GICD_ITARGETSR0..7 because SGI/PPI target
registers hold no state (read-only on MP, RAZ/WI on UP).
- Add a runtime GICC_APRn quiescence check after disabling the CPU
interface, and restore GICC_CTLR before returning -EBUSY.
Changes in V8:
- disable cpu interface + distributor before suspend
- change 0xffffffff to GENMASK;
- cosmetic changes;
Changes in V7:
- Allocate one contiguous memory block for the GICv2 dist suspend context.
- gicv2_resume() no longer unconditionally re-enables the distributor/CPU
interface; it now writes back the saved CTLR values as-is.
- gicv2_alloc_context() now returns 0 on success and panics on failure,
since suspend context allocation is not recoverable.
---
xen/arch/arm/gic-v2.c | 232 ++++++++++++++++++++++++++++++++-
xen/arch/arm/gic.c | 29 +++++
xen/arch/arm/include/asm/gic.h | 12 ++
3 files changed, 271 insertions(+), 2 deletions(-)
diff --git a/xen/arch/arm/gic-v2.c b/xen/arch/arm/gic-v2.c
index 87eda9d322..67caf1c70a 100644
--- a/xen/arch/arm/gic-v2.c
+++ b/xen/arch/arm/gic-v2.c
@@ -118,12 +118,12 @@ static inline void writeb_gicd(uint8_t val, unsigned int offset)
writeb_relaxed(val, gicv2.map_dbase + offset);
}
-static inline void writel_gicd(uint32_t val, unsigned int offset)
+static inline void writel_gicd(uint32_t val, size_t offset)
{
writel_relaxed(val, gicv2.map_dbase + offset);
}
-static inline uint32_t readl_gicd(unsigned int offset)
+static inline uint32_t readl_gicd(size_t offset)
{
return readl_relaxed(gicv2.map_dbase + offset);
}
@@ -1108,6 +1108,225 @@ static int gicv2_iomem_deny_access(struct domain *d)
return iomem_deny_access(d, mfn, mfn + nr - 1);
}
+#ifdef CONFIG_SYSTEM_SUSPEND
+
+/* This struct represents block of 32 IRQs */
+struct irq_block {
+ uint32_t icfgr[2]; /* 2 registers of 16 IRQs each */
+ uint32_t ipriorityr[8];
+ uint32_t isenabler;
+ uint32_t isactiver;
+ uint32_t itargetsr[8];
+};
+
+/* GICv2 registers to be saved/restored on system suspend/resume */
+struct gicv2_context {
+ /* GICC context */
+ struct cpu_ctx {
+ uint32_t ctlr;
+ uint32_t pmr;
+ uint32_t bpr;
+ } cpu;
+
+ /* GICD context */
+ struct dist_ctx {
+ uint32_t ctlr;
+ /* Includes banked SGI/PPI state for the boot CPU. */
+ struct irq_block *irqs;
+ } dist;
+};
+
+static struct gicv2_context gic_ctx;
+
+#define GICV2_NR_APRS 4
+#define GICV2_APR_BITS_PER_REG 32U
+
+static int gicv2_check_active_priorities(uint32_t bpr)
+{
+ unsigned int i, apr_bits, nr_aprs;
+
+ /*
+ * Xen writes GICC_BPR to 0 during CPU init and does not change it. Per
+ * IHI0048B.b, a write below the implementation minimum reads back as the
+ * minimum supported BPR value. Table 4-47 maps that Xen-visible BPR value
+ * to the visible GICC_APR<n> bits. Avoid reading APR registers outside
+ * that visible range.
+ *
+ * This covers both GICv2 with and without Security Extensions.
+ */
+ apr_bits = 1U << (7 - (bpr & 0x7));
+ nr_aprs = DIV_ROUND_UP(apr_bits, GICV2_APR_BITS_PER_REG);
+
+ ASSERT(nr_aprs <= GICV2_NR_APRS);
+
+ for ( i = 0; i < nr_aprs; i++ )
+ {
+ unsigned int bits = min(GICV2_APR_BITS_PER_REG,
+ apr_bits - i * GICV2_APR_BITS_PER_REG);
+ uint32_t mask = (uint32_t)GENMASK(bits - 1, 0);
+ uint32_t apr = readl_gicc(GICC_APR + i * 4) & mask;
+
+ if ( !apr )
+ continue;
+
+ printk(XENLOG_ERR "GICv2: suspend aborted: GICC_APR%u=%#08x\n",
+ i, apr);
+ return -EBUSY;
+ }
+
+ return 0;
+}
+
+static int gicv2_suspend(void)
+{
+ unsigned int i, blocks = DIV_ROUND_UP(gicv2_info.nr_lines, 32);
+ int ret;
+
+ /*
+ * Keep the CPU interface and Distributor control state unchanged.
+ * Firmware may use them to detect pending interrupts and wakeup events
+ * before entering system suspend. Local IRQs are already disabled.
+ */
+ gic_ctx.cpu.ctlr = readl_gicc(GICC_CTLR);
+ gic_ctx.cpu.bpr = readl_gicc(GICC_BPR);
+
+ /*
+ * Check the active-priority state for the group Xen drives through the
+ * CPU interface. GICC_CTL_ENABLE enables Group 0 without SecurityExtn and
+ * Group 1 in Xen's Non-secure view with SecurityExtn, and in both cases
+ * the relevant state is visible through GICC_APRn. The APR layout is
+ * implementation-defined, so only test the bits visible from Xen's CPU
+ * interface view instead of reading every possible APR register.
+ */
+ ret = gicv2_check_active_priorities(gic_ctx.cpu.bpr);
+ if ( ret )
+ return ret;
+
+ gic_ctx.cpu.pmr = readl_gicc(GICC_PMR);
+
+ /*
+ * Do not save PPI/SPI pending state. Drivers must quiesce non-wakeup
+ * sources and handle or retain earlier events before this point. The
+ * platform must retain wakeup events outside the GIC if its state can
+ * be lost, including edge events during suspend entry. Level sources
+ * still asserted after resume become pending again.
+ */
+ gic_ctx.dist.ctlr = readl_gicd(GICD_CTLR);
+
+ for ( i = 0; i < blocks; i++ )
+ {
+ struct irq_block *irqs = gic_ctx.dist.irqs + i;
+ size_t j, off = i * sizeof(irqs->isenabler);
+ size_t nr_regs = ARRAY_SIZE(irqs->ipriorityr);
+
+ if ( i == blocks - 1 )
+ nr_regs = DIV_ROUND_UP(gicv2_info.nr_lines - i * 32, 4);
+
+ irqs->isenabler = readl_gicd(GICD_ISENABLER + off);
+
+ /*
+ * Save distributor active state as part of the hypervisor-owned
+ * physical interrupt state. In GICv2 EOImode==1, EOIR only drops the
+ * priority; final deactivation is separate. For guest-routed
+ * interrupts, Xen may have EOIed the physical IRQ while the guest/vGIC
+ * side still owns the deactivate step. Therefore GICD_ISACTIVER can
+ * legitimately remain set even though transient SGI pending state and
+ * CPU-interface active-priority state are expected to be quiesced here.
+ */
+ irqs->isactiver = readl_gicd(GICD_ISACTIVER + off);
+
+ off = i * sizeof(irqs->ipriorityr);
+ for ( j = 0; j < nr_regs; j++ )
+ irqs->ipriorityr[j] = readl_gicd(GICD_IPRIORITYR + off + j * 4);
+
+ /*
+ * GICD_ITARGETSR0..7 cover SGIs/PPIs and hold no state to save:
+ * they are read-only on multiprocessor implementations and RAZ/WI
+ * on uniprocessor implementations.
+ */
+ if ( i )
+ {
+ off = i * sizeof(irqs->itargetsr);
+ for ( j = 0; j < nr_regs; j++ )
+ irqs->itargetsr[j] = readl_gicd(GICD_ITARGETSR + off + j * 4);
+ }
+
+ off = i * sizeof(irqs->icfgr);
+ for ( j = 0; j < ARRAY_SIZE(irqs->icfgr); j++ )
+ irqs->icfgr[j] = readl_gicd(GICD_ICFGR + off + j * 4);
+ }
+
+ return 0;
+}
+
+static void gicv2_resume(void)
+{
+ unsigned int i, blocks = DIV_ROUND_UP(gicv2_info.nr_lines, 32);
+
+ gicv2_cpu_disable();
+ /* Disable distributor */
+ writel_gicd(0, GICD_CTLR);
+
+ for ( i = 0; i < blocks; i++ )
+ {
+ struct irq_block *irqs = gic_ctx.dist.irqs + i;
+ size_t j, off = i * sizeof(irqs->isenabler);
+ size_t nr_regs = ARRAY_SIZE(irqs->ipriorityr);
+
+ if ( i == blocks - 1 )
+ nr_regs = DIV_ROUND_UP(gicv2_info.nr_lines - i * 32, 4);
+
+ writel_gicd(GENMASK(31, 0), GICD_ICENABLER + off);
+
+ off = i * sizeof(irqs->icfgr);
+ for ( j = 0; j < ARRAY_SIZE(irqs->icfgr); j++ )
+ writel_gicd(irqs->icfgr[j], GICD_ICFGR + off + j * 4);
+
+ off = i * sizeof(irqs->ipriorityr);
+ for ( j = 0; j < nr_regs; j++ )
+ writel_gicd(irqs->ipriorityr[j], GICD_IPRIORITYR + off + j * 4);
+
+ /*
+ * GICD_ITARGETSR0..7 cover SGIs/PPIs and hold no state to save:
+ * they are read-only on multiprocessor implementations and RAZ/WI
+ * on uniprocessor implementations.
+ */
+ if ( i )
+ {
+ off = i * sizeof(irqs->itargetsr);
+ for ( j = 0; j < nr_regs; j++ )
+ writel_gicd(irqs->itargetsr[j], GICD_ITARGETSR + off + j * 4);
+ }
+
+ off = i * sizeof(irqs->isenabler);
+ writel_gicd(irqs->isenabler, GICD_ISENABLER + off);
+
+ writel_gicd(GENMASK(31, 0), GICD_ICACTIVER + off);
+ writel_gicd(irqs->isactiver, GICD_ISACTIVER + off);
+ }
+
+ /* Restore distributor control state. */
+ writel_gicd(gic_ctx.dist.ctlr, GICD_CTLR);
+
+ /* Restore GIC CPU interface configuration */
+ writel_gicc(gic_ctx.cpu.pmr, GICC_PMR);
+ writel_gicc(gic_ctx.cpu.bpr, GICC_BPR);
+
+ /* Enable GIC CPU interface */
+ writel_gicc(gic_ctx.cpu.ctlr, GICC_CTLR);
+}
+
+static void __init gicv2_alloc_context(void)
+{
+ uint32_t blocks = DIV_ROUND_UP(gicv2_info.nr_lines, 32);
+
+ gic_ctx.dist.irqs = xzalloc_array(struct irq_block, blocks);
+ if ( !gic_ctx.dist.irqs )
+ panic("Failed to allocate memory for GICv2 suspend context\n");
+}
+
+#endif /* CONFIG_SYSTEM_SUSPEND */
+
#ifdef CONFIG_ACPI
static unsigned long gicv2_get_hwdom_extra_madt_size(const struct domain *d)
{
@@ -1315,6 +1534,11 @@ static int __init gicv2_init(void)
spin_unlock(&gicv2.lock);
+#ifdef CONFIG_SYSTEM_SUSPEND
+ /* Allocate memory to be used for saving GIC context during the suspend */
+ gicv2_alloc_context();
+#endif /* CONFIG_SYSTEM_SUSPEND */
+
return 0;
}
@@ -1358,6 +1582,10 @@ static const struct gic_hw_operations gicv2_ops = {
.map_hwdom_extra_mappings = gicv2_map_hwdom_extra_mappings,
.iomem_deny_access = gicv2_iomem_deny_access,
.do_LPI = gicv2_do_LPI,
+#ifdef CONFIG_SYSTEM_SUSPEND
+ .suspend = gicv2_suspend,
+ .resume = gicv2_resume,
+#endif /* CONFIG_SYSTEM_SUSPEND */
};
/* Set up the GIC */
diff --git a/xen/arch/arm/gic.c b/xen/arch/arm/gic.c
index c4bda435bd..30087b5938 100644
--- a/xen/arch/arm/gic.c
+++ b/xen/arch/arm/gic.c
@@ -464,6 +464,35 @@ int gic_iomem_deny_access(struct domain *d)
return gic_hw_ops->iomem_deny_access(d);
}
+#ifdef CONFIG_SYSTEM_SUSPEND
+
+int gic_suspend(void)
+{
+ /* Must be called by boot CPU#0 with interrupts disabled */
+ ASSERT(!local_irq_is_enabled());
+ ASSERT(!smp_processor_id());
+
+ if ( !gic_hw_ops->suspend || !gic_hw_ops->resume )
+ return -ENOSYS;
+
+ return gic_hw_ops->suspend();
+}
+
+void gic_resume(void)
+{
+ /*
+ * Must be called by boot CPU#0 with interrupts disabled after gic_suspend
+ * has returned successfully.
+ */
+ ASSERT(!local_irq_is_enabled());
+ ASSERT(!smp_processor_id());
+ ASSERT(gic_hw_ops->resume);
+
+ gic_hw_ops->resume();
+}
+
+#endif /* CONFIG_SYSTEM_SUSPEND */
+
static int cpu_gic_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
diff --git a/xen/arch/arm/include/asm/gic.h b/xen/arch/arm/include/asm/gic.h
index 7ceae49774..6997fac5e3 100644
--- a/xen/arch/arm/include/asm/gic.h
+++ b/xen/arch/arm/include/asm/gic.h
@@ -307,6 +307,12 @@ extern int gicv_setup(struct domain *d);
extern void gic_save_state(struct vcpu *v);
extern void gic_restore_state(struct vcpu *v);
+#ifdef CONFIG_SYSTEM_SUSPEND
+/* Suspend/resume */
+extern int gic_suspend(void);
+extern void gic_resume(void);
+#endif /* CONFIG_SYSTEM_SUSPEND */
+
/* SGI (AKA IPIs) */
enum gic_sgi {
GIC_SGI_EVENT_CHECK,
@@ -458,6 +464,12 @@ struct gic_hw_operations {
int (*iomem_deny_access)(struct domain *d);
/* Handle LPIs, which require special handling */
void (*do_LPI)(unsigned int lpi);
+#ifdef CONFIG_SYSTEM_SUSPEND
+ /* Save GIC configuration due to the system suspend */
+ int (*suspend)(void);
+ /* Restore GIC configuration due to the system resume */
+ void (*resume)(void);
+#endif /* CONFIG_SYSTEM_SUSPEND */
};
extern const struct gic_hw_operations *gic_hw_ops;
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v14 03/15] xen/arm: gic-v3: tolerate retained redistributor LPI state across CPU_OFF
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
2026-11-17 1:04 ` [PATCH v14 01/15] xen/arm: Add suspend and resume timer helpers Mykola Kvach
2026-11-17 1:04 ` [PATCH v14 02/15] xen/arm: gic-v2: Implement GIC suspend/resume functions Mykola Kvach
@ 2026-11-17 1:04 ` Mykola Kvach
2026-11-17 1:04 ` [PATCH v14 04/15] xen/percpu: defer freeing per-CPU areas after resume failures Mykola Kvach
` (11 subsequent siblings)
14 siblings, 0 replies; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:04 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk, Luca Fancellu
PSCI does not guarantee that a GICv3 redistributor is powered down across
CPU_OFF -> CPU_ON.
DEN0022F.b says CPU_OFF powers down the calling core (5.5) and CPU_ON
brings the core back with a defined initial CPU state (5.6, 6.4).
However, PSCI leaves interrupt migration and GIC re-initialization to the
supervisory software/firmware stack: the caller must migrate interrupts
away before CPU_OFF (5.5.2), and the execution context that is lost in a
powerdown state must be saved and restored by software (6.8). PSCI also
calls out GIC management explicitly in 6.8, including retargeting SPIs,
preventing PPIs/SGIs from targeting a powered down CPU, and reinitializing
the CPU interface after CPU_ON.
This matches the GIC architecture. IHI0069H.b Chapter 11.1 requires the PE
and CPU interface to share a power domain, but explicitly allows the
associated redistributor, distributor, and ITS to remain powered while the
PE and CPU interface are off. All other GIC power-management behavior is
IMPLEMENTATION DEFINED. DEN0050D Chapter 4.2, "Generic Interrupt
Controller (GIC)", says the GICv3 redistributor may live either in the AP
core power domain or in a relatively always-on parent domain. So after
CPU_OFF -> CPU_ON a secondary CPU can legitimately come back to a live
redistributor with GICR_CTLR.EnableLPIs still set.
Handle that case in the LPI setup path instead of assuming a fully reset
redistributor.
The LPI path needs special care because the GIC spec makes redistributor
LPI state sticky and partially implementation defined. IHI0069H.b 5.1.1
and 5.1.2 say that changing GICR_PROPBASER or GICR_PENDBASER while
GICR_CTLR.EnableLPIs == 1 is UNPREDICTABLE. After clearing EnableLPIs,
software must wait for GICR_CTLR.RWP == 0 before touching the pending
table. The architecture also permits implementations where, once
EnableLPIs has been set, clearing it again is not guaranteed to work.
Where an ITS is present, the spec strongly recommends moving LPIs to
another redistributor before clearing EnableLPIs.
Because of that, treat a retained EnableLPIs state as valid when the
redistributor still points at Xen's expected PROPBASER/PENDBASER tables.
Only try to clear EnableLPIs when the retained configuration does not
match Xen's state, and wait for RWP before reprogramming the tables.
This is also consistent with platform firmware reality: PSCI and the GIC
architecture allow platform-specific redistributor power handling, and not
all platform firmware implementations force a full redistributor power-off
through implementation-defined controls during CPU_OFF. Xen therefore needs
to tolerate retained redistributor state on secondary CPU bring-up.
Keep gicv3_populate_rdist() resident as well, because gicv3_cpu_init()
reuses it on secondary CPU bring-up after init.
Tested using Xen's non-boot CPU disable/enable path on Arm
FVP_Base_RevC-2xAEMvA, both with and without:
-C gic_distributor.allow-LPIEN-clear=1
-C gic_distributor.GICR-clear-enable-supported=1
and on Orange Pi 5.
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Luca Fancellu <luca.fancellu@arm.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
---
Changes in v13:
- Document the pending-table lifetime requirement for CPU hotplug.
Changes in v10:
- Drop unrelated gicv3_populate_rdist() printk() format cleanups to keep
the patch focused on retained redistributor LPI state.
Changes in v9:
- move gicv3_do_wait_for_rwp prototype from its related header to gic.h
- drop __init from gicv3_populate_rdist(), which is reused on secondary
CPU bring-up after boot
- changed print format for smp_processor_id in gicv3_populate_rdist func
- cosmetic changes
---
xen/arch/arm/gic-v3-lpi.c | 84 +++++++++++++++++++++++++++++++++-
xen/arch/arm/gic-v3.c | 15 ++++--
xen/arch/arm/include/asm/gic.h | 4 ++
3 files changed, 97 insertions(+), 6 deletions(-)
diff --git a/xen/arch/arm/gic-v3-lpi.c b/xen/arch/arm/gic-v3-lpi.c
index 1cf49430ea..1a893d3ab2 100644
--- a/xen/arch/arm/gic-v3-lpi.c
+++ b/xen/arch/arm/gic-v3-lpi.c
@@ -76,6 +76,13 @@ static struct {
struct lpi_redist_data {
paddr_t redist_addr;
unsigned int redist_id;
+ /*
+ * System suspend keeps the per-CPU area and this table.
+ * TODO: CPU hotplug must handle the table's lifetime when freeing the
+ * per-CPU area. A redistributor may still use it with EnableLPIs set,
+ * so the table must remain allocated and its pointer must be retained
+ * until the redistributor no longer uses it.
+ */
void *pending_table;
};
@@ -99,6 +106,13 @@ static uint32_t __ro_after_init host_lpi_flags;
#define MAX_NR_HOST_LPIS (lpi_data.max_host_lpi_ids - LPI_OFFSET)
#define HOST_LPIS_PER_PAGE (PAGE_SIZE / sizeof(union host_lpi))
+#define GICR_PROPBASER_XEN_MASK GENMASK_ULL(51, 12)
+/*
+ * For retained redistributor state, match the pending table by address only.
+ * Attribute bits such as PTZ may not read back with the programmed value.
+ */
+#define GICR_PENDBASER_XEN_MASK GENMASK_ULL(51, 16)
+
void __init gicv3_lpi_update_host_flags(uint32_t flags)
{
host_lpi_flags |= flags;
@@ -337,6 +351,60 @@ static int gicv3_lpi_set_pendtable(void __iomem *rdist_base)
return 0;
}
+static uint64_t gicv3_lpi_expected_proptable(void)
+{
+ return virt_to_maddr(lpi_data.lpi_property);
+}
+
+static uint64_t gicv3_lpi_expected_pendtable(void)
+{
+ return virt_to_maddr(this_cpu(lpi_redist).pending_table);
+}
+
+static bool gicv3_lpi_tables_match(void __iomem *rdist_base)
+{
+ uint64_t propbase, pendbase;
+
+ if ( !lpi_data.lpi_property || !this_cpu(lpi_redist).pending_table )
+ return false;
+
+ propbase = readq_relaxed(rdist_base + GICR_PROPBASER);
+ pendbase = readq_relaxed(rdist_base + GICR_PENDBASER);
+
+ return ((propbase & GICR_PROPBASER_XEN_MASK) ==
+ (gicv3_lpi_expected_proptable() & GICR_PROPBASER_XEN_MASK)) &&
+ ((pendbase & GICR_PENDBASER_XEN_MASK) ==
+ (gicv3_lpi_expected_pendtable() & GICR_PENDBASER_XEN_MASK));
+}
+
+static int gicv3_lpi_disable_lpis(void __iomem *rdist_base)
+{
+ uint32_t reg = readl_relaxed(rdist_base + GICR_CTLR);
+ int ret;
+
+ if ( !(reg & GICR_CTLR_ENABLE_LPIS) )
+ return 0;
+
+ writel_relaxed(reg & ~GICR_CTLR_ENABLE_LPIS, rdist_base + GICR_CTLR);
+
+ /*
+ * The spec only guarantees programmability when we have observed the bit
+ * cleared. Where clearing is supported, RWP must reach 0 before touching
+ * PROPBASER/PENDBASER again.
+ */
+ wmb();
+
+ ret = gicv3_do_wait_for_rwp(rdist_base, GICR_CTLR_RWP);
+ if ( ret )
+ return ret;
+
+ reg = readl_relaxed(rdist_base + GICR_CTLR);
+ if ( reg & GICR_CTLR_ENABLE_LPIS )
+ return -EBUSY;
+
+ return 0;
+}
+
/*
* Tell a redistributor about the (shared) property table, allocating one
* if not already done.
@@ -419,7 +487,21 @@ int gicv3_lpi_init_rdist(void __iomem * rdist_base)
/* Make sure LPIs are disabled before setting up the tables. */
reg = readl_relaxed(rdist_base + GICR_CTLR);
if ( reg & GICR_CTLR_ENABLE_LPIS )
- return -EBUSY;
+ {
+ if ( gicv3_lpi_tables_match(rdist_base) )
+ return -EBUSY;
+
+ ret = gicv3_lpi_disable_lpis(rdist_base);
+ if ( ret == -EBUSY )
+ {
+ printk(XENLOG_ERR
+ "GICv3: CPU%u: LPIs still enabled with unexpected redistributor tables\n",
+ smp_processor_id());
+ return -EINVAL;
+ }
+ if ( ret )
+ return ret;
+ }
ret = gicv3_lpi_set_pendtable(rdist_base);
if ( ret )
diff --git a/xen/arch/arm/gic-v3.c b/xen/arch/arm/gic-v3.c
index cca49d2a2a..7e4b485f11 100644
--- a/xen/arch/arm/gic-v3.c
+++ b/xen/arch/arm/gic-v3.c
@@ -293,7 +293,7 @@ static void gicv3_enable_sre(void)
}
/* Wait for completion of a distributor/redistributor change */
-static void gicv3_do_wait_for_rwp(void __iomem *base, uint32_t rwp_bit)
+int gicv3_do_wait_for_rwp(void __iomem *base, uint32_t rwp_bit)
{
uint32_t val;
bool timeout = false;
@@ -317,17 +317,22 @@ static void gicv3_do_wait_for_rwp(void __iomem *base, uint32_t rwp_bit)
} while ( 1 );
if ( timeout )
+ {
dprintk(XENLOG_ERR, "RWP timeout\n");
+ return -ETIMEDOUT;
+ }
+
+ return 0;
}
static void gicv3_dist_wait_for_rwp(void)
{
- gicv3_do_wait_for_rwp(GICD, GICD_CTLR_RWP);
+ (void)gicv3_do_wait_for_rwp(GICD, GICD_CTLR_RWP);
}
static void gicv3_redist_wait_for_rwp(void)
{
- gicv3_do_wait_for_rwp(GICD_RDIST_BASE, GICR_CTLR_RWP);
+ (void)gicv3_do_wait_for_rwp(GICD_RDIST_BASE, GICR_CTLR_RWP);
}
static void gicv3_wait_for_rwp(int irq)
@@ -883,7 +888,7 @@ static bool gicv3_enable_lpis(void)
return true;
}
-static int __init gicv3_populate_rdist(void)
+static int gicv3_populate_rdist(void)
{
int i;
uint32_t aff;
@@ -951,7 +956,7 @@ static int __init gicv3_populate_rdist(void)
gicv3_set_redist_address(rdist_addr, procnum);
ret = gicv3_lpi_init_rdist(ptr);
- if ( ret && ret != -ENODEV )
+ if ( ret && ret != -ENODEV && ret != -EBUSY )
{
printk("GICv3: CPU%d: Cannot initialize LPIs: %u\n",
smp_processor_id(), ret);
diff --git a/xen/arch/arm/include/asm/gic.h b/xen/arch/arm/include/asm/gic.h
index 6997fac5e3..4051fad5b4 100644
--- a/xen/arch/arm/include/asm/gic.h
+++ b/xen/arch/arm/include/asm/gic.h
@@ -307,6 +307,10 @@ extern int gicv_setup(struct domain *d);
extern void gic_save_state(struct vcpu *v);
extern void gic_restore_state(struct vcpu *v);
+#ifdef CONFIG_GICV3
+int gicv3_do_wait_for_rwp(void __iomem *base, uint32_t rwp_bit);
+#endif
+
#ifdef CONFIG_SYSTEM_SUSPEND
/* Suspend/resume */
extern int gic_suspend(void);
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v14 04/15] xen/percpu: defer freeing per-CPU areas after resume failures
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (2 preceding siblings ...)
2026-11-17 1:04 ` [PATCH v14 03/15] xen/arm: gic-v3: tolerate retained redistributor LPI state across CPU_OFF Mykola Kvach
@ 2026-11-17 1:04 ` Mykola Kvach
2026-11-18 1:51 ` Volodymyr Babchuk
2026-11-17 1:04 ` [PATCH v14 05/15] xen/arm: gic-v3: Implement GICv3 suspend/resume functions Mykola Kvach
` (10 subsequent siblings)
14 siblings, 1 reply; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:04 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Andrew Cooper, Anthony PERARD, Michal Orzel,
Jan Beulich, Julien Grall, Roger Pau Monné,
Stefano Stabellini
When a CPU fails to come back during system resume, cpu_up() sends
CPU_UP_CANCELED. After trying the other CPUs, enable_nonboot_cpus()
sends CPU_RESUME_FAILED for the same CPU.
On architectures which do not park offline CPUs, both notifications
queue free_percpu_area(). The release metadata, including the rcu_head,
is stored in that CPU's per-CPU area. The first callback may already
have freed the area when the second notification arrives, or the same
rcu_head may be queued twice. The CPU_RESUME_FAILED callbacks also need
the area to clean up timers and CPU-pool state.
Skip the per-CPU release for CPU_UP_CANCELED during resume. Let
CPU_RESUME_FAILED release the area after the other cleanup callbacks.
This prepares the common code for Arm system suspend. x86 parks offline
CPUs, so the per-CPU notifier does not call free_percpu_area() for either
CPU_UP_CANCELED or CPU_RESUME_FAILED.
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
---
Changes in V14:
- Clarify that x86 skips free_percpu_area() for CPU_UP_CANCELED and
CPU_RESUME_FAILED.
- Remove the blank line after fallthrough. No functional change.
Changes in v13:
- New patch.
---
xen/common/percpu.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/xen/common/percpu.c b/xen/common/percpu.c
index f180f37253..757de111db 100644
--- a/xen/common/percpu.c
+++ b/xen/common/percpu.c
@@ -82,6 +82,14 @@ static int cf_check cpu_percpu_callback(
break;
case CPU_UP_CANCELED:
+ /*
+ * On resume, CPU_RESUME_FAILED is sent after all CPUs have been
+ * tried. Keep the area alive for its cleanup callbacks and let
+ * that notification release it.
+ */
+ if ( system_state == SYS_STATE_resume )
+ break;
+ fallthrough;
case CPU_DEAD:
case CPU_RESUME_FAILED:
if ( !park_offline_cpus && system_state != SYS_STATE_suspend )
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* Re: [PATCH v14 04/15] xen/percpu: defer freeing per-CPU areas after resume failures
2026-11-17 1:04 ` [PATCH v14 04/15] xen/percpu: defer freeing per-CPU areas after resume failures Mykola Kvach
@ 2026-11-18 1:51 ` Volodymyr Babchuk
0 siblings, 0 replies; 20+ messages in thread
From: Volodymyr Babchuk @ 2026-11-18 1:51 UTC (permalink / raw)
To: Mykola Kvach
Cc: xen-devel@lists.xenproject.org, Andrew Cooper, Anthony PERARD,
Michal Orzel, Jan Beulich, Julien Grall, Roger Pau Monné,
Stefano Stabellini, Juergen Gross
Hi,
CC'ed Juergen, because I have a question about cpupools.
Mykola Kvach <Mykola_Kvach@epam.com> writes:
> When a CPU fails to come back during system resume, cpu_up() sends
> CPU_UP_CANCELED. After trying the other CPUs, enable_nonboot_cpus()
> sends CPU_RESUME_FAILED for the same CPU.
>
> On architectures which do not park offline CPUs, both notifications
> queue free_percpu_area(). The release metadata, including the rcu_head,
> is stored in that CPU's per-CPU area. The first callback may already
> have freed the area when the second notification arrives, or the same
> rcu_head may be queued twice. The CPU_RESUME_FAILED callbacks also need
> the area to clean up timers and CPU-pool state.
A bit convoluted. As I see, problem is caused by the fact
CPU_UP_CANCELED is a terminal state in a "simple" CPU up sequence, but
is a transient state in a system resume sequence. As such, theoretically
other per_cpu callbacks might have a similar issue when they don't
expect one more "CPU state is bad" callback. I can see that
common/timer.c also tries to handle both callbacks as terminal
ones. Probably, you need a similar fix there as well.
Actually, I am not sure why do we need CPU_RESUME_FAILED in the first
place. As I can see, only cpupool handles it in a sensible way. Which
begs a question: why cpupool can't call cpupool_cpu_remove_forced() on
CPU_UP_CANCELED instead?
>
> Skip the per-CPU release for CPU_UP_CANCELED during resume. Let
> CPU_RESUME_FAILED release the area after the other cleanup callbacks.
>
> This prepares the common code for Arm system suspend. x86 parks offline
> CPUs, so the per-CPU notifier does not call free_percpu_area() for either
> CPU_UP_CANCELED or CPU_RESUME_FAILED.
>
> Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
> ---
> Changes in V14:
> - Clarify that x86 skips free_percpu_area() for CPU_UP_CANCELED and
> CPU_RESUME_FAILED.
> - Remove the blank line after fallthrough. No functional change.
>
> Changes in v13:
> - New patch.
> ---
> xen/common/percpu.c | 8 ++++++++
> 1 file changed, 8 insertions(+)
>
> diff --git a/xen/common/percpu.c b/xen/common/percpu.c
> index f180f37253..757de111db 100644
> --- a/xen/common/percpu.c
> +++ b/xen/common/percpu.c
> @@ -82,6 +82,14 @@ static int cf_check cpu_percpu_callback(
> break;
>
> case CPU_UP_CANCELED:
> + /*
> + * On resume, CPU_RESUME_FAILED is sent after all CPUs have been
> + * tried. Keep the area alive for its cleanup callbacks and let
> + * that notification release it.
> + */
> + if ( system_state == SYS_STATE_resume )
> + break;
> + fallthrough;
> case CPU_DEAD:
> case CPU_RESUME_FAILED:
> if ( !park_offline_cpus && system_state != SYS_STATE_suspend )
--
WBR, Volodymyr
^ permalink raw reply [flat|nested] 20+ messages in thread
* [PATCH v14 05/15] xen/arm: gic-v3: Implement GICv3 suspend/resume functions
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (3 preceding siblings ...)
2026-11-17 1:04 ` [PATCH v14 04/15] xen/percpu: defer freeing per-CPU areas after resume failures Mykola Kvach
@ 2026-11-17 1:04 ` Mykola Kvach
2026-11-17 1:04 ` [PATCH v14 06/15] xen/arm: gic-v3: add ITS suspend/resume support Mykola Kvach
` (9 subsequent siblings)
14 siblings, 0 replies; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:04 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk
System suspend may lead to a state where GIC would be powered down.
Therefore, Xen should save/restore the context of GIC on suspend/resume.
Note that the context consists of states of registers which are
controlled by the hypervisor. Other GIC registers which are accessible
by guests are saved/restored on context switch.
Before continuing suspend, also verify that the physical CPU interface
has no Group 1 active-priority state left. Use ICC_CTLR_EL1.PRIbits to
decide which ICC_AP1R<n>_EL1 registers are implemented, so Xen does not
read an unimplemented AP1R register.
Have gicv3_suspend() panic if the Redistributor does not set
GICR_WAKER.ChildrenAsleep before the timeout. Clearing ProcessorSleep
while ChildrenAsleep is still zero is UNPREDICTABLE, so Xen cannot safely
undo this transition and restore the CPU interface. Keep error reporting
in gicv3_disable_redist(), including the CPU.
Check active priorities before disabling the CPU and virtual interfaces,
while local IRQs are masked. Return directly on failure, without changing
the interfaces or requesting Redistributor sleep.
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
---
Changes in V14:
- no functional changes;
- reduce length of lines.
Changes in V13:
- Use uint32_t for the CTLR argument of the active-priority check (MISRA
Rule 10.3). No functional change.
- Cast saved CPU register values to uint32_t to avoid implicit narrowing
(MISRA Rule 10.3). No functional change.
- Rename the SPI/eSPI helper parameters from is_espi to espi so they do not
hide the is_espi() helper declared in asm/irq.h. Use the same name for
the GET_SPI_REG_OFFSET() macro parameter (MISRA Rule 5.3). No functional
change.
- Rename nr_irqs to nr_block_irqs in all SPI block helpers and in
gicv3_suspend()/gicv3_resume() to avoid hiding the global nr_irqs (MISRA
Rule 5.3). No functional change.
- Panic in gicv3_suspend() if the Redistributor sleep request times out.
- Log the CPU at error level on a sleep timeout.
- Check active priorities before disabling the interfaces and return
directly on failure. This is safe because local IRQs are already
masked: Xen's IRQ handler cannot acknowledge new interrupts, and
pending interrupts alone do not change active priorities.
- Capitalize the comments noted in review.
- Use fallthrough instead of comments in the active-priority check.
Changes in V10:
- abort suspend when the physical Group 1 active-priority state is still
present, deriving accessible ICC_AP1R<n>_EL1 registers from
ICC_CTLR_EL1.PRIbits;
- re-enable the redistributor before restoring CPU and virtual interface
state on the suspend abort path;
- panic if the redistributor cannot be re-enabled on the suspend abort path;
- avoid saving/restoring reserved GICD_IPRIORITYR and GICD_IROUTER entries
for a partially populated last SPI block;
- disable Distributor group forwarding while preserving affinity routing
state before restoring Distributor configuration;
- disable SPI/eSPI forwarding and wait for RWP before restoring
GICD_ICFGR<n>.Int_config.
Changes in V9:
- fix the suspend-context comment typo and split dist_ctx declarations;
- restore ICC_IGRPEN1_EL1 on the suspend error path;
- re-initialize GICD_IGROUPRnE during resume;
- restore GICD_IROUTER only after re-enabling ARE_NS during resume.
Changes in V8:
- use right rdist base for prop/pend baser and ctrl
Changes in V7:
- restore LPI regs on resume
- add timeout during redist disabling
- squash with suspend/resume handling for GICv3 eSPI registers
- drop ITS guard paths so suspend/resume always runs; switch missing ctx
allocation to panic
- trim TODO comments; narrow redistributor storage to PPI icfgr
- keep distributor context allocation even without ITS; adjust resume
to use GENMASK(31, 0) for clearing enables
- drop storage of the SGI configuration register, as SGIs are always
edge-triggered
---
xen/arch/arm/gic-v3-lpi.c | 3 +
xen/arch/arm/gic-v3.c | 456 ++++++++++++++++++++++-
xen/arch/arm/include/asm/arm64/sysregs.h | 5 +
xen/arch/arm/include/asm/gic_v3_defs.h | 3 +
4 files changed, 464 insertions(+), 3 deletions(-)
diff --git a/xen/arch/arm/gic-v3-lpi.c b/xen/arch/arm/gic-v3-lpi.c
index 1a893d3ab2..3dd07db007 100644
--- a/xen/arch/arm/gic-v3-lpi.c
+++ b/xen/arch/arm/gic-v3-lpi.c
@@ -519,6 +519,9 @@ static int cpu_callback(struct notifier_block *nfb, unsigned long action,
switch ( action )
{
case CPU_UP_PREPARE:
+ if ( system_state == SYS_STATE_resume )
+ break;
+
rc = gicv3_lpi_allocate_pendtable(cpu);
if ( rc )
printk(XENLOG_ERR "Unable to allocate the pendtable for CPU%lu\n",
diff --git a/xen/arch/arm/gic-v3.c b/xen/arch/arm/gic-v3.c
index 7e4b485f11..c00b5322c4 100644
--- a/xen/arch/arm/gic-v3.c
+++ b/xen/arch/arm/gic-v3.c
@@ -1128,12 +1128,12 @@ out:
return res;
}
-static void gicv3_hyp_disable(void)
+static void gicv3_hyp_enable(bool enable)
{
register_t hcr;
hcr = READ_SYSREG(ICH_HCR_EL2);
- hcr &= ~GICH_HCR_EN;
+ hcr = enable ? (hcr | GICH_HCR_EN) : (hcr & ~GICH_HCR_EN);
WRITE_SYSREG(hcr, ICH_HCR_EL2);
isb();
}
@@ -1240,7 +1240,7 @@ static void gicv3_disable_interface(void)
spin_lock(&gicv3.lock);
gicv3_cpu_disable();
- gicv3_hyp_disable();
+ gicv3_hyp_enable(false);
spin_unlock(&gicv3.lock);
}
@@ -1979,6 +1979,448 @@ static bool gic_dist_supports_lpis(void)
return (readl_relaxed(GICD + GICD_TYPER) & GICD_TYPE_LPIS);
}
+#ifdef CONFIG_SYSTEM_SUSPEND
+
+/* This struct represents a block of 32 IRQs */
+struct dist_irq_block {
+ uint32_t icfgr[2];
+ uint32_t ipriorityr[8];
+ uint64_t irouter[32];
+ uint32_t isactiver;
+ uint32_t isenabler;
+};
+
+struct redist_ctx {
+ uint32_t ctlr;
+ uint32_t icfgr; /* Only PPIs stored */
+ uint32_t igroupr;
+ uint32_t ipriorityr[8];
+ uint32_t isactiver;
+ uint32_t isenabler;
+
+ uint64_t pendbase;
+ uint64_t propbase;
+};
+
+/* GICv3 registers to be saved/restored on system suspend/resume */
+struct gicv3_ctx {
+ struct dist_ctx {
+ uint32_t ctlr;
+ struct dist_irq_block *irqs;
+ struct dist_irq_block *espi_irqs;
+ } dist;
+
+ /* Have only one rdist structure for last running CPU during suspend */
+ struct redist_ctx rdist;
+
+ struct cpu_ctx {
+ uint32_t ctlr;
+ uint32_t pmr;
+ uint32_t bpr;
+ uint32_t sre_el2;
+ uint32_t grpen;
+ } cpu;
+};
+
+static struct gicv3_ctx gicv3_ctx;
+
+static void __init gicv3_alloc_context(void)
+{
+ uint32_t blocks = DIV_ROUND_UP(gicv3_info.nr_lines, 32);
+
+ /* The spec allows for systems without any SPIs */
+ if ( blocks > 1 )
+ {
+ gicv3_ctx.dist.irqs = xzalloc_array(struct dist_irq_block, blocks - 1);
+ if ( !gicv3_ctx.dist.irqs )
+ panic("Failed to allocate memory for GICv3 suspend context\n");
+ }
+
+#ifdef CONFIG_GICV3_ESPI
+ if ( !gic_number_espis() )
+ return;
+
+ blocks = gic_number_espis() / 32;
+ gicv3_ctx.dist.espi_irqs = xzalloc_array(struct dist_irq_block, blocks);
+ if ( !gicv3_ctx.dist.espi_irqs )
+ panic("Failed to allocate memory for GICv3 eSPI suspend context\n");
+#endif
+}
+
+static int gicv3_disable_redist(void)
+{
+ void __iomem *waker = GICD_RDIST_BASE + GICR_WAKER;
+ s_time_t deadline;
+
+ /*
+ * Avoid infinite loop if Non-secure does not have access to GICR_WAKER.
+ * See Arm IHI 0069H.b, 12.11.42 GICR_WAKER:
+ * When GICD_CTLR.DS == 0 and an access is Non-secure accesses to this
+ * register are RAZ/WI.
+ */
+ if ( !(readl_relaxed(GICD + GICD_CTLR) & GICD_CTLR_DS) )
+ return 0;
+
+ deadline = NOW() + MILLISECS(1000);
+
+ writel_relaxed(readl_relaxed(waker) | GICR_WAKER_ProcessorSleep, waker);
+ while ( (readl_relaxed(waker) & GICR_WAKER_ChildrenAsleep) == 0 )
+ {
+ if ( NOW() > deadline )
+ {
+ printk(XENLOG_ERR "GICv3: CPU%u: Redistributor sleep timeout\n",
+ smp_processor_id());
+ return -ETIMEDOUT;
+ }
+
+ cpu_relax();
+ udelay(10);
+ }
+
+ return 0;
+}
+
+#define GET_SPI_REG_OFFSET(name, espi) \
+ ((espi) ? GICD_##name##nE : GICD_##name)
+
+static void gicv3_store_spi_irq_block(struct dist_irq_block *irqs,
+ unsigned int i,
+ unsigned int nr_block_irqs, bool espi)
+{
+ void __iomem *base;
+ unsigned int irq, nr_priority_regs;
+
+ ASSERT(nr_block_irqs && nr_block_irqs <= 32);
+ nr_priority_regs = DIV_ROUND_UP(nr_block_irqs, 4);
+
+ base = GICD + GET_SPI_REG_OFFSET(ICFGR, espi) + i * sizeof(irqs->icfgr);
+ irqs->icfgr[0] = readl_relaxed(base);
+ irqs->icfgr[1] = readl_relaxed(base + 4);
+
+ base = GICD + GET_SPI_REG_OFFSET(IPRIORITYR, espi);
+ base += i * sizeof(irqs->ipriorityr);
+ for ( irq = 0; irq < nr_priority_regs; irq++ )
+ irqs->ipriorityr[irq] = readl_relaxed(base + 4 * irq);
+
+ base = GICD + GET_SPI_REG_OFFSET(IROUTER, espi);
+ base += i * sizeof(irqs->irouter);
+ for ( irq = 0; irq < nr_block_irqs; irq++ )
+ irqs->irouter[irq] = readq_relaxed_non_atomic(base + 8 * irq);
+
+ base = GICD + GET_SPI_REG_OFFSET(ISACTIVER, espi);
+ base += i * sizeof(irqs->isactiver);
+ irqs->isactiver = readl_relaxed(base);
+
+ base = GICD + GET_SPI_REG_OFFSET(ISENABLER, espi);
+ base += i * sizeof(irqs->isenabler);
+ irqs->isenabler = readl_relaxed(base);
+}
+
+static void gicv3_restore_spi_irq_config(struct dist_irq_block *irqs,
+ unsigned int i,
+ unsigned int nr_block_irqs, bool espi)
+{
+ void __iomem *base;
+ unsigned int irq, nr_priority_regs;
+
+ ASSERT(nr_block_irqs && nr_block_irqs <= 32);
+ nr_priority_regs = DIV_ROUND_UP(nr_block_irqs, 4);
+
+ base = GICD + GET_SPI_REG_OFFSET(ICFGR, espi) + i * sizeof(irqs->icfgr);
+ writel_relaxed(irqs->icfgr[0], base);
+ writel_relaxed(irqs->icfgr[1], base + 4);
+
+ base = GICD + GET_SPI_REG_OFFSET(IPRIORITYR, espi);
+ base += i * sizeof(irqs->ipriorityr);
+ for ( irq = 0; irq < nr_priority_regs; irq++ )
+ writel_relaxed(irqs->ipriorityr[irq], base + 4 * irq);
+}
+
+static void gicv3_restore_spi_irq_routing(struct dist_irq_block *irqs,
+ unsigned int i,
+ unsigned int nr_block_irqs, bool espi)
+{
+ void __iomem *base;
+ unsigned int irq;
+
+ ASSERT(nr_block_irqs && nr_block_irqs <= 32);
+
+ base = GICD + GET_SPI_REG_OFFSET(IROUTER, espi);
+ base += i * sizeof(irqs->irouter);
+ for ( irq = 0; irq < nr_block_irqs; irq++ )
+ writeq_relaxed_non_atomic(irqs->irouter[irq], base + 8 * irq);
+}
+
+static void gicv3_disable_spi_irq_block(unsigned int i, bool espi)
+{
+ void __iomem *base;
+
+ base = GICD + GET_SPI_REG_OFFSET(ICENABLER, espi) + i * 4;
+ writel_relaxed(GENMASK(31, 0), base);
+}
+
+static void gicv3_restore_spi_irq_state(struct dist_irq_block *irqs,
+ unsigned int i, bool espi)
+{
+ void __iomem *base;
+
+ base = GICD + GET_SPI_REG_OFFSET(ISENABLER, espi);
+ base += i * sizeof(irqs->isenabler);
+ writel_relaxed(irqs->isenabler, base);
+
+ base = GICD + GET_SPI_REG_OFFSET(ICACTIVER, espi) + i * 4;
+ writel_relaxed(GENMASK(31, 0), base);
+
+ base = GICD + GET_SPI_REG_OFFSET(ISACTIVER, espi);
+ base += i * sizeof(irqs->isactiver);
+ writel_relaxed(irqs->isactiver, base);
+}
+
+static int gicv3_check_ap1r(unsigned int n, register_t apr)
+{
+ if ( !apr )
+ return 0;
+
+ printk(XENLOG_ERR "GICv3: suspend aborted: ICC_AP1R%u_EL1=%#"
+ PRIregister"\n", n, apr);
+
+ return -EBUSY;
+}
+
+static int gicv3_check_active_priorities(uint32_t ctlr)
+{
+ unsigned int pribits = MASK_EXTR(ctlr, ICC_CTLR_EL1_PRIBITS_MASK) + 1;
+ int ret;
+
+ /*
+ * Xen enables physical Group 1 interrupts through ICC_IGRPEN1_EL1,
+ * so only the physical Group 1 active-priority registers are relevant
+ * here. Use ICC_CTLR_EL1.PRIbits for the physical CPU interface, not
+ * ICH_VTR_EL2, which describes the virtual interface. ICC_AP1R1_EL1 is
+ * only implemented with at least 6 physical priority bits, and
+ * ICC_AP1R2_EL1/ICC_AP1R3_EL1 with at least 7.
+ */
+ switch ( pribits )
+ {
+ case 8:
+ case 7:
+ ret = gicv3_check_ap1r(3, READ_SYSREG(ICC_AP1R3_EL1));
+ if ( ret )
+ return ret;
+ ret = gicv3_check_ap1r(2, READ_SYSREG(ICC_AP1R2_EL1));
+ if ( ret )
+ return ret;
+ fallthrough;
+ case 6:
+ ret = gicv3_check_ap1r(1, READ_SYSREG(ICC_AP1R1_EL1));
+ if ( ret )
+ return ret;
+ fallthrough;
+ default:
+ return gicv3_check_ap1r(0, READ_SYSREG(ICC_AP1R0_EL1));
+ }
+}
+
+static int gicv3_suspend(void)
+{
+ unsigned int i, nr_block_irqs;
+ void __iomem *base;
+ int ret;
+ struct redist_ctx *rdist = &gicv3_ctx.rdist;
+
+ /* Save GICC configuration */
+ gicv3_ctx.cpu.ctlr = (uint32_t)READ_SYSREG(ICC_CTLR_EL1);
+ gicv3_ctx.cpu.pmr = (uint32_t)READ_SYSREG(ICC_PMR_EL1);
+ gicv3_ctx.cpu.bpr = (uint32_t)READ_SYSREG(ICC_BPR1_EL1);
+ gicv3_ctx.cpu.sre_el2 = (uint32_t)READ_SYSREG(ICC_SRE_EL2);
+ gicv3_ctx.cpu.grpen = (uint32_t)READ_SYSREG(ICC_IGRPEN1_EL1);
+
+ ret = gicv3_check_active_priorities(gicv3_ctx.cpu.ctlr);
+ if ( ret )
+ return ret;
+
+ gicv3_disable_interface();
+
+ ret = gicv3_disable_redist();
+ if ( ret )
+ {
+ /*
+ * Clearing ProcessorSleep before ChildrenAsleep is set is
+ * UNPREDICTABLE, so do not try to restore the CPU interface.
+ */
+ panic("GICv3: Cannot safely abort suspend after a sleep timeout\n");
+ }
+
+ /* Save GICR configuration */
+ gicv3_redist_wait_for_rwp();
+
+ base = GICD_RDIST_BASE;
+
+ rdist->ctlr = readl_relaxed(base + GICR_CTLR);
+
+ rdist->propbase = readq_relaxed(base + GICR_PROPBASER);
+ rdist->pendbase = readq_relaxed(base + GICR_PENDBASER);
+
+ base = GICD_RDIST_SGI_BASE;
+
+ /* Save priority on PPI and SGI interrupts */
+ for ( i = 0; i < NR_GIC_LOCAL_IRQS / 4; i++ )
+ rdist->ipriorityr[i] = readl_relaxed(base + GICR_IPRIORITYR0 + 4 * i);
+
+ rdist->isactiver = readl_relaxed(base + GICR_ISACTIVER0);
+ rdist->isenabler = readl_relaxed(base + GICR_ISENABLER0);
+ rdist->igroupr = readl_relaxed(base + GICR_IGROUPR0);
+ rdist->icfgr = readl_relaxed(base + GICR_ICFGR1);
+
+ /* Save GICD configuration */
+ gicv3_dist_wait_for_rwp();
+ gicv3_ctx.dist.ctlr = readl_relaxed(GICD + GICD_CTLR);
+
+ for ( i = 1; i < DIV_ROUND_UP(gicv3_info.nr_lines, 32); i++ )
+ {
+ nr_block_irqs = min(32U, gicv3_info.nr_lines - i * 32);
+ gicv3_store_spi_irq_block(gicv3_ctx.dist.irqs + i - 1, i, nr_block_irqs,
+ false);
+ }
+
+#ifdef CONFIG_GICV3_ESPI
+ for ( i = 0; i < gic_number_espis() / 32; i++ )
+ gicv3_store_spi_irq_block(gicv3_ctx.dist.espi_irqs + i, i, 32, true);
+#endif
+
+ return 0;
+}
+
+static void gicv3_resume(void)
+{
+ int ret;
+ unsigned int i, nr_block_irqs;
+ uint32_t dist_ctlr;
+ void __iomem *base;
+ struct redist_ctx *rdist = &gicv3_ctx.rdist;
+
+ dist_ctlr = gicv3_ctx.dist.ctlr & GICD_CTLR_ARE_NS;
+
+ /* Disable group forwarding while preserving affinity routing state. */
+ writel_relaxed(dist_ctlr, GICD + GICD_CTLR);
+ gicv3_dist_wait_for_rwp();
+
+ /*
+ * IHI0069H.b 12.9.9 says changing GICD_ICFGR<n>.Int_config
+ * while the interrupt is individually enabled is UNPREDICTABLE.
+ * Disable SPIs first; 4.7.1 defines GICD_ICENABLER<n>, n > 0,
+ * as the per-SPI disable mechanism.
+ */
+ for ( i = 1; i < DIV_ROUND_UP(gicv3_info.nr_lines, 32); i++ )
+ gicv3_disable_spi_irq_block(i, false);
+
+#ifdef CONFIG_GICV3_ESPI
+ for ( i = 0; i < gic_number_espis() / 32; i++ )
+ gicv3_disable_spi_irq_block(i, true);
+#endif
+
+ gicv3_dist_wait_for_rwp();
+
+ for ( i = NR_GIC_LOCAL_IRQS; i < gicv3_info.nr_lines; i += 32 )
+ writel_relaxed(GENMASK(31, 0), GICD + GICD_IGROUPR + (i / 32) * 4);
+
+ for ( i = 1; i < DIV_ROUND_UP(gicv3_info.nr_lines, 32); i++ )
+ {
+ nr_block_irqs = min(32U, gicv3_info.nr_lines - i * 32);
+ gicv3_restore_spi_irq_config(gicv3_ctx.dist.irqs + i - 1, i,
+ nr_block_irqs, false);
+ }
+
+#ifdef CONFIG_GICV3_ESPI
+ for ( i = 0; i < gic_number_espis() / 32; i++ )
+ {
+ writel_relaxed(GENMASK(31, 0), GICD + GICD_IGROUPRnE + i * 4);
+ gicv3_restore_spi_irq_config(gicv3_ctx.dist.espi_irqs + i, i, 32,
+ true);
+ }
+#endif
+
+ if ( dist_ctlr )
+ {
+ for ( i = 1; i < DIV_ROUND_UP(gicv3_info.nr_lines, 32); i++ )
+ {
+ nr_block_irqs = min(32U, gicv3_info.nr_lines - i * 32);
+ gicv3_restore_spi_irq_routing(gicv3_ctx.dist.irqs + i - 1, i,
+ nr_block_irqs, false);
+ }
+
+#ifdef CONFIG_GICV3_ESPI
+ for ( i = 0; i < gic_number_espis() / 32; i++ )
+ gicv3_restore_spi_irq_routing(gicv3_ctx.dist.espi_irqs + i, i,
+ 32, true);
+#endif
+ }
+
+ for ( i = 1; i < DIV_ROUND_UP(gicv3_info.nr_lines, 32); i++ )
+ gicv3_restore_spi_irq_state(gicv3_ctx.dist.irqs + i - 1, i, false);
+
+#ifdef CONFIG_GICV3_ESPI
+ for ( i = 0; i < gic_number_espis() / 32; i++ )
+ gicv3_restore_spi_irq_state(gicv3_ctx.dist.espi_irqs + i, i, true);
+#endif
+
+ writel_relaxed(gicv3_ctx.dist.ctlr, GICD + GICD_CTLR);
+ gicv3_dist_wait_for_rwp();
+
+ ret = gicv3_lpi_init_rdist(GICD_RDIST_BASE);
+ /*
+ * If LPIs are already enabled, assume firmware or the still-powered
+ * redistributor has valid PROPBASER/PENDBASER and skip reprogramming.
+ * Return -EBUSY so callers can ignore this case.
+ */
+ if ( ret && ret != -ENODEV && ret != -EBUSY )
+ panic("GICv3: Failed to re-initialize LPIs during resume\n");
+ else if ( ret == -EBUSY ) /* Extra checks, just to be sure */
+ {
+ base = GICD_RDIST_BASE;
+ if ( readq_relaxed(base + GICR_PROPBASER) != rdist->propbase ||
+ readq_relaxed(base + GICR_PENDBASER) != rdist->pendbase )
+ panic("GICv3: LPIs already enabled with unexpected PROPBASER/PENDBASER during resume\n");
+ }
+
+ /* Restore GICR (Redistributor) configuration */
+ if ( gicv3_enable_redist() )
+ panic("GICv3: Failed to re-enable redistributor during resume\n");
+
+ base = GICD_RDIST_SGI_BASE;
+
+ writel_relaxed(GENMASK(31, 0), base + GICR_ICENABLER0);
+ gicv3_redist_wait_for_rwp();
+
+ for ( i = 0; i < NR_GIC_LOCAL_IRQS / 4; i++ )
+ writel_relaxed(rdist->ipriorityr[i], base + GICR_IPRIORITYR0 + i * 4);
+
+ writel_relaxed(rdist->isactiver, base + GICR_ISACTIVER0);
+ writel_relaxed(rdist->igroupr, base + GICR_IGROUPR0);
+ writel_relaxed(rdist->icfgr, base + GICR_ICFGR1);
+
+ gicv3_redist_wait_for_rwp();
+
+ writel_relaxed(rdist->isenabler, base + GICR_ISENABLER0);
+ writel_relaxed(rdist->ctlr, GICD_RDIST_BASE + GICR_CTLR);
+
+ gicv3_redist_wait_for_rwp();
+
+ WRITE_SYSREG(gicv3_ctx.cpu.sre_el2, ICC_SRE_EL2);
+ isb();
+
+ /* Restore CPU interface (System registers) */
+ WRITE_SYSREG(gicv3_ctx.cpu.pmr, ICC_PMR_EL1);
+ WRITE_SYSREG(gicv3_ctx.cpu.bpr, ICC_BPR1_EL1);
+ WRITE_SYSREG(gicv3_ctx.cpu.ctlr, ICC_CTLR_EL1);
+ WRITE_SYSREG(gicv3_ctx.cpu.grpen, ICC_IGRPEN1_EL1);
+ isb();
+
+ gicv3_hyp_init();
+}
+
+#endif /* CONFIG_SYSTEM_SUSPEND */
+
/* Set up the GIC */
static int __init gicv3_init(void)
{
@@ -2053,6 +2495,10 @@ static int __init gicv3_init(void)
gicv3_hyp_init();
+#ifdef CONFIG_SYSTEM_SUSPEND
+ gicv3_alloc_context();
+#endif
+
out:
spin_unlock(&gicv3.lock);
@@ -2092,6 +2538,10 @@ static const struct gic_hw_operations gicv3_ops = {
#endif
.iomem_deny_access = gicv3_iomem_deny_access,
.do_LPI = gicv3_do_LPI,
+#ifdef CONFIG_SYSTEM_SUSPEND
+ .suspend = gicv3_suspend,
+ .resume = gicv3_resume,
+#endif
};
static int __init gicv3_dt_preinit(struct dt_device_node *node, const void *data)
diff --git a/xen/arch/arm/include/asm/arm64/sysregs.h b/xen/arch/arm/include/asm/arm64/sysregs.h
index f6ece8f972..ae2476426c 100644
--- a/xen/arch/arm/include/asm/arm64/sysregs.h
+++ b/xen/arch/arm/include/asm/arm64/sysregs.h
@@ -16,6 +16,11 @@
#define ICC_SRE_EL1 S3_0_C12_C12_5
#define ICC_IGRPEN1_EL1 S3_0_C12_C12_7
+#define ICC_AP1R0_EL1 S3_0_C12_C9_0
+#define ICC_AP1R1_EL1 S3_0_C12_C9_1
+#define ICC_AP1R2_EL1 S3_0_C12_C9_2
+#define ICC_AP1R3_EL1 S3_0_C12_C9_3
+
#define ICH_VSEIR_EL2 S3_4_C12_C9_4
#define ICC_SRE_EL2 S3_4_C12_C9_5
#define ICH_HCR_EL2 S3_4_C12_C11_0
diff --git a/xen/arch/arm/include/asm/gic_v3_defs.h b/xen/arch/arm/include/asm/gic_v3_defs.h
index 2081b2fe8f..1cf3758386 100644
--- a/xen/arch/arm/include/asm/gic_v3_defs.h
+++ b/xen/arch/arm/include/asm/gic_v3_defs.h
@@ -92,12 +92,15 @@
#define GICD_TYPE_LPIS (1U << 17)
#define GICD_CTLR_RWP (1UL << 31)
+#define GICD_CTLR_DS (1U << 6)
#define GICD_CTLR_ARE_NS (1U << 4)
#define GICD_CTLR_ENABLE_G1A (1U << 1)
#define GICD_CTLR_ENABLE_G1 (1U << 0)
#define GICD_IROUTER_SPI_MODE_ANY (1UL << 31)
#define GICC_CTLR_EL1_EOImode_drop (1U << 1)
+#define ICC_CTLR_EL1_PRIBITS_SHIFT 8
+#define ICC_CTLR_EL1_PRIBITS_MASK (0x7U << ICC_CTLR_EL1_PRIBITS_SHIFT)
#define GICR_WAKER_ProcessorSleep (1U << 1)
#define GICR_WAKER_ChildrenAsleep (1U << 2)
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v14 06/15] xen/arm: gic-v3: add ITS suspend/resume support
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (4 preceding siblings ...)
2026-11-17 1:04 ` [PATCH v14 05/15] xen/arm: gic-v3: Implement GICv3 suspend/resume functions Mykola Kvach
@ 2026-11-17 1:04 ` Mykola Kvach
2026-11-17 1:04 ` [PATCH v14 07/15] xen/arm: tee: keep init_tee_secondary() for hotplug and resume Mykola Kvach
` (8 subsequent siblings)
14 siblings, 0 replies; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:04 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk, Andrew Cooper, Anthony PERARD,
Jan Beulich, Roger Pau Monné, Luca Fancellu
Handle system suspend/resume for GICv3 with an ITS present so LPIs keep
working after firmware powers the GIC down.
Save and restore the ITS CTLR, CBASER and BASER registers. On resume,
re-establish the collection mapping only when the collection is held in
the ITS itself. Memory-backed collections are restored through the
restored GITS_BASER tables and must not be remapped unconditionally.
Add list_for_each_entry_continue_reverse() in list.h for the ITS suspend
error path that needs to roll back partially saved state.
Based on Linux commit dba0bc7b76dc:
"irqchip/gic-v3-its: Add ability to save/restore ITS state".
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Luca Fancellu <luca.fancellu@arm.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com> # Arm code
---
Changes in V13:
- Cast GITS_CTLR_QUIESCENT to uint32_t before inverting the mask, so the
operation matches the 32-bit CTLR value (MISRA Rule 10.3). No functional
change.
Changes in V10:
- Replay MAPC on resume only for collections held in the ITS itself, as
indicated by GITS_TYPER.HCC. Memory-backed collections are restored
through GITS_BASER and are no longer remapped unconditionally.
- Make the current Xen col_id == cpu assumption explicit in the ITS
resume path.
- Use "unpredictable" instead of "undefined" in the CBASER/BASER restore
comment.
Changes in V9:
- fix the ITS suspend/resume coding-style nits;
- preserve the saved GITS_CTLR state while masking the read-only
QUIESCENT bit.
Changes in V8:
- Reword the CBASER/CWRITER comment to match Xen and drop the stale Linux
cmd_write reference.
- Clarify the list_for_each_entry_continue_reverse() comment.
- Factor out per-ITS helpers for collection setup and resume.
- Restore each ITS and re-establish its collection mapping in the same
loop, so a failed ITS resume is not followed by MAPC/SYNC on that
un-restored instance.
- panic in case when resume of an ITS failed
- cleanup baser cache during suspend
---
xen/arch/arm/gic-v3-its.c | 146 ++++++++++++++++++++++++--
xen/arch/arm/gic-v3.c | 13 +++
xen/arch/arm/include/asm/gic_v3_its.h | 28 +++++
xen/include/xen/list.h | 14 +++
4 files changed, 192 insertions(+), 9 deletions(-)
diff --git a/xen/arch/arm/gic-v3-its.c b/xen/arch/arm/gic-v3-its.c
index f44ee21293..f214a52ad4 100644
--- a/xen/arch/arm/gic-v3-its.c
+++ b/xen/arch/arm/gic-v3-its.c
@@ -375,6 +375,22 @@ static int its_send_cmd_inv(struct host_its *its,
return its_send_command(its, cmd);
}
+static int gicv3_its_setup_collection_single(struct host_its *its,
+ unsigned int cpu)
+{
+ int ret;
+
+ ret = its_send_cmd_mapc(its, cpu, cpu);
+ if ( ret )
+ return ret;
+
+ ret = its_send_cmd_sync(its, cpu);
+ if ( ret )
+ return ret;
+
+ return gicv3_its_wait_commands(its);
+}
+
/* Set up the (1:1) collection mapping for the given host CPU. */
int gicv3_its_setup_collection(unsigned int cpu)
{
@@ -383,15 +399,7 @@ int gicv3_its_setup_collection(unsigned int cpu)
list_for_each_entry(its, &host_its_list, entry)
{
- ret = its_send_cmd_mapc(its, cpu, cpu);
- if ( ret )
- return ret;
-
- ret = its_send_cmd_sync(its, cpu);
- if ( ret )
- return ret;
-
- ret = gicv3_its_wait_commands(its);
+ ret = gicv3_its_setup_collection_single(its, cpu);
if ( ret )
return ret;
}
@@ -1276,6 +1284,126 @@ int __init gicv3_its_init(unsigned int host_lpi_bits)
return 0;
}
+#ifdef CONFIG_SYSTEM_SUSPEND
+int gicv3_its_suspend(void)
+{
+ struct host_its *its;
+ int ret;
+
+ list_for_each_entry( its, &host_its_list, entry )
+ {
+ unsigned int i;
+ void __iomem *base = its->its_base;
+
+ /*
+ * By the time Xen reaches gic_suspend(), every domain is already in
+ * SHUTDOWN_suspend, so ITS-targeting interrupt sources are expected
+ * to have been quiesced by the owning OS before SYSTEM_SUSPEND.
+ */
+ /* Preserve saved GITS_CTLR state, excluding read-only QUIESCENT. */
+ its->suspend_ctx.ctlr = readl_relaxed(base + GITS_CTLR) &
+ ~(uint32_t)GITS_CTLR_QUIESCENT;
+ ret = gicv3_disable_its(its);
+ if ( ret )
+ {
+ writel_relaxed(its->suspend_ctx.ctlr, base + GITS_CTLR);
+ goto err;
+ }
+
+ its->suspend_ctx.cbaser = readq_relaxed(base + GITS_CBASER);
+
+ for ( i = 0; i < GITS_BASER_NR_REGS; i++ )
+ {
+ uint64_t baser = readq_relaxed(base + GITS_BASER0 + i * 8);
+
+ its->suspend_ctx.baser[i] = 0;
+
+ if ( !(baser & GITS_VALID_BIT) )
+ continue;
+
+ its->suspend_ctx.baser[i] = baser;
+ }
+ }
+
+ return 0;
+
+ err:
+ list_for_each_entry_continue_reverse( its, &host_its_list, entry )
+ writel_relaxed(its->suspend_ctx.ctlr, its->its_base + GITS_CTLR);
+
+ return ret;
+}
+
+static int gicv3_its_resume_single(struct host_its *its, unsigned int cpu)
+{
+ void __iomem *base = its->its_base;
+ unsigned int i;
+ int ret;
+ uint64_t typer;
+ unsigned int col_id = cpu; /* Xen currently uses col_id == cpu. */
+
+ /*
+ * Make sure that the ITS is disabled. If it fails to quiesce,
+ * don't restore it since writing to CBASER or BASER<n>
+ * registers is unpredictable according to the GIC v3 ITS
+ * Specification.
+ */
+ WARN_ON(readl_relaxed(base + GITS_CTLR) & GITS_CTLR_ENABLE);
+ ret = gicv3_disable_its(its);
+ if ( ret )
+ return ret;
+
+ writeq_relaxed(its->suspend_ctx.cbaser, base + GITS_CBASER);
+
+ /*
+ * Writing CBASER resets CREADR to 0, so reset CWRITER to
+ * keep the command queue pointers aligned.
+ */
+ writeq_relaxed(0, base + GITS_CWRITER);
+
+ /* Restore GITS_BASER from the value cache. */
+ for ( i = 0; i < GITS_BASER_NR_REGS; i++ )
+ {
+ uint64_t baser = its->suspend_ctx.baser[i];
+
+ if ( !(baser & GITS_VALID_BIT) )
+ continue;
+
+ writeq_relaxed(baser, base + GITS_BASER0 + i * 8);
+ }
+
+ writel_relaxed(its->suspend_ctx.ctlr, base + GITS_CTLR);
+
+ typer = readq_relaxed(base + GITS_TYPER);
+
+ /*
+ * Only collections with IDs below HCC are held in the ITS itself
+ * and lose their state across an ITS reset/power loss. Memory-backed
+ * collections are restored by restoring GITS_BASER and must not be
+ * remapped here.
+ */
+ if ( col_id < GITS_TYPER_HCC(typer) )
+ return gicv3_its_setup_collection_single(its, cpu);
+
+ return 0;
+}
+
+void gicv3_its_resume(void)
+{
+ struct host_its *its;
+ unsigned int cpu = smp_processor_id();
+ int ret;
+
+ list_for_each_entry( its, &host_its_list, entry )
+ {
+ ret = gicv3_its_resume_single(its, cpu);
+ if ( ret )
+ panic("GICv3: ITS@%"PRIpaddr": failed to restore during resume: %d\n",
+ its->addr, ret);
+ }
+}
+
+#endif /* CONFIG_SYSTEM_SUSPEND */
/*
* Local variables:
diff --git a/xen/arch/arm/gic-v3.c b/xen/arch/arm/gic-v3.c
index c00b5322c4..184209826d 100644
--- a/xen/arch/arm/gic-v3.c
+++ b/xen/arch/arm/gic-v3.c
@@ -2241,6 +2241,10 @@ static int gicv3_suspend(void)
gicv3_disable_interface();
+ ret = gicv3_its_suspend();
+ if ( ret )
+ goto out_enable_iface;
+
ret = gicv3_disable_redist();
if ( ret )
{
@@ -2289,6 +2293,13 @@ static int gicv3_suspend(void)
#endif
return 0;
+
+ out_enable_iface:
+ gicv3_hyp_enable(true);
+ WRITE_SYSREG(gicv3_ctx.cpu.grpen, ICC_IGRPEN1_EL1);
+ isb();
+
+ return ret;
}
static void gicv3_resume(void)
@@ -2406,6 +2417,8 @@ static void gicv3_resume(void)
gicv3_redist_wait_for_rwp();
+ gicv3_its_resume();
+
WRITE_SYSREG(gicv3_ctx.cpu.sre_el2, ICC_SRE_EL2);
isb();
diff --git a/xen/arch/arm/include/asm/gic_v3_its.h b/xen/arch/arm/include/asm/gic_v3_its.h
index edc002f187..cb730b3845 100644
--- a/xen/arch/arm/include/asm/gic_v3_its.h
+++ b/xen/arch/arm/include/asm/gic_v3_its.h
@@ -43,6 +43,11 @@
#define GITS_CTLR_QUIESCENT BIT(31, UL)
#define GITS_CTLR_ENABLE BIT(0, UL)
+#define GITS_TYPER_HCC_SHIFT 24
+#define GITS_TYPER_HCC_MASK 0xffUL
+#define GITS_TYPER_HCC(r) (((r) >> GITS_TYPER_HCC_SHIFT) & \
+ GITS_TYPER_HCC_MASK)
+
#define GITS_TYPER_PTA BIT(19, UL)
#define GITS_TYPER_DEVIDS_SHIFT 13
#define GITS_TYPER_DEVIDS_MASK (0x1fUL << GITS_TYPER_DEVIDS_SHIFT)
@@ -135,6 +140,13 @@ struct host_its {
*/
uint32_t quirk_flags;
unsigned int flags;
+#ifdef CONFIG_SYSTEM_SUSPEND
+ struct suspend_ctx {
+ uint32_t ctlr;
+ uint64_t cbaser;
+ uint64_t baser[GITS_BASER_NR_REGS];
+ } suspend_ctx;
+#endif
};
/* Map a collection for this host CPU to each host ITS. */
@@ -211,6 +223,11 @@ uint64_t gicv3_mem_get_cacheability(uint32_t flags);
uint64_t gicv3_mem_get_shareability(uint32_t flags);
unsigned int gicv3_mem_get_alloc_flags(uint32_t flags);
+#ifdef CONFIG_SYSTEM_SUSPEND
+int gicv3_its_suspend(void);
+void gicv3_its_resume(void);
+#endif
+
#else
#ifdef CONFIG_ACPI
@@ -273,6 +290,17 @@ static inline int gicv3_its_make_hwdom_dt_nodes(const struct domain *d,
return 0;
}
+#ifdef CONFIG_SYSTEM_SUSPEND
+static inline int gicv3_its_suspend(void)
+{
+ return 0;
+}
+
+static inline void gicv3_its_resume(void)
+{
+}
+#endif
+
#endif /* CONFIG_HAS_ITS */
#endif
diff --git a/xen/include/xen/list.h b/xen/include/xen/list.h
index 98d8482dab..2aab274157 100644
--- a/xen/include/xen/list.h
+++ b/xen/include/xen/list.h
@@ -535,6 +535,20 @@ static inline void list_splice_init(struct list_head *list,
&(pos)->member != (head); \
(pos) = list_entry((pos)->member.next, typeof(*(pos)), member))
+/**
+ * list_for_each_entry_continue_reverse - iterate backwards from the given point
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Iterate over list of given type backwards, starting from the element previous
+ * to the current one in list order.
+ */
+#define list_for_each_entry_continue_reverse(pos, head, member) \
+ for ((pos) = list_entry((pos)->member.prev, typeof(*(pos)), member); \
+ &(pos)->member != (head); \
+ (pos) = list_entry((pos)->member.prev, typeof(*(pos)), member))
+
/**
* list_for_each_entry_from - iterate over list of given type from the
* current point
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v14 07/15] xen/arm: tee: keep init_tee_secondary() for hotplug and resume
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (5 preceding siblings ...)
2026-11-17 1:04 ` [PATCH v14 06/15] xen/arm: gic-v3: add ITS suspend/resume support Mykola Kvach
@ 2026-11-17 1:04 ` Mykola Kvach
2026-11-17 1:04 ` [PATCH v14 08/15] xen/arm: ffa: fix notification SRI across CPU hotplug/suspend Mykola Kvach
` (7 subsequent siblings)
14 siblings, 0 replies; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:04 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Volodymyr Babchuk, Bertrand Marquis, Jens Wiklander,
Stefano Stabellini, Julien Grall, Michal Orzel, Luca Fancellu
init_tee_secondary() was marked __init and freed after boot. Calling it
from the CPU hotplug/resume path then executed discarded code, which
could crash Xen. Drop __init so the TEE mediator secondary init can run
safely on hotplugged and resumed CPUs.
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Luca Fancellu <luca.fancellu@arm.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
Reviewed-by: Volodymyr Babchuk <volodymyr_babchuk@epam.com>
---
xen/arch/arm/tee/tee.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/xen/arch/arm/tee/tee.c b/xen/arch/arm/tee/tee.c
index 8501443c8e..00e561fc78 100644
--- a/xen/arch/arm/tee/tee.c
+++ b/xen/arch/arm/tee/tee.c
@@ -128,7 +128,7 @@ static int __init tee_init(void)
presmp_initcall(tee_init);
-void __init init_tee_secondary(void)
+void init_tee_secondary(void)
{
if ( cur_mediator && cur_mediator->ops->init_secondary )
cur_mediator->ops->init_secondary();
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v14 08/15] xen/arm: ffa: fix notification SRI across CPU hotplug/suspend
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (6 preceding siblings ...)
2026-11-17 1:04 ` [PATCH v14 07/15] xen/arm: tee: keep init_tee_secondary() for hotplug and resume Mykola Kvach
@ 2026-11-17 1:04 ` Mykola Kvach
2026-11-17 1:04 ` [PATCH v14 09/15] iommu/ipmmu-vmsa: Implement suspend/resume callbacks Mykola Kvach
` (6 subsequent siblings)
14 siblings, 0 replies; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:04 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Volodymyr Babchuk, Bertrand Marquis, Jens Wiklander,
Stefano Stabellini, Julien Grall, Michal Orzel, Luca Fancellu
The FF-A notification SRI interrupt handler was not correctly tied to
CPU hotplug and suspend/resume. As a result, CPUs going offline and
back online could end up with stale or missing handlers, breaking
delivery of FF-A notifications.
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Luca Fancellu <luca.fancellu@arm.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
---
Changes in V13:
- Use false for free_on_release (MISRA Rule 10.3). No functional change.
- Explicitly discard request_sri_irq()'s result on secondary CPUs. The
helper logs errors, preserving the existing behavior (MISRA Rule 17.7).
No functional change.
- Explain why the notifier ignores other CPU events (MISRA Rule 16.4). No
functional change.
---
xen/arch/arm/tee/ffa_notif.c | 63 +++++++++++++++++++++++++++++-------
1 file changed, 51 insertions(+), 12 deletions(-)
diff --git a/xen/arch/arm/tee/ffa_notif.c b/xen/arch/arm/tee/ffa_notif.c
index c64bc39f03..1ec455d2ad 100644
--- a/xen/arch/arm/tee/ffa_notif.c
+++ b/xen/arch/arm/tee/ffa_notif.c
@@ -360,10 +360,28 @@ static int32_t ffa_notification_bitmap_destroy(uint16_t vm_id)
return ffa_simple_call(FFA_NOTIFICATION_BITMAP_DESTROY, vm_id, 0, 0, 0);
}
-void ffa_notif_init_interrupt(void)
+static DEFINE_PER_CPU_READ_MOSTLY(struct irqaction, sri_irq);
+
+static int request_sri_irq(void)
{
int ret;
+ struct irqaction *sri_action = &this_cpu(sri_irq);
+
+ sri_action->name = "FF-A notif";
+ sri_action->handler = notif_irq_handler;
+ sri_action->dev_id = NULL;
+ sri_action->free_on_release = false;
+
+ ret = setup_irq(notif_sri_irq, 0, sri_action);
+ if ( ret )
+ printk(XENLOG_ERR "ffa: setup_irq irq %u failed: error %d\n",
+ notif_sri_irq, ret);
+
+ return ret;
+}
+void ffa_notif_init_interrupt(void)
+{
if ( fw_notif_enabled && notif_sri_irq < NR_GIC_SGI )
{
/*
@@ -376,14 +394,37 @@ void ffa_notif_init_interrupt(void)
* pending, while the SPMC in the secure world will not notice that
* the interrupt was lost.
*/
- ret = request_irq(notif_sri_irq, 0, notif_irq_handler, "FF-A notif",
- NULL);
- if ( ret )
- printk(XENLOG_ERR "ffa: request_irq irq %u failed: error %d\n",
- notif_sri_irq, ret);
+ (void)request_sri_irq();
+ }
+}
+
+static void deinit_ffa_notif_interrupt(void)
+{
+ if ( fw_notif_enabled && notif_sri_irq < NR_GIC_SGI )
+ release_irq(notif_sri_irq, NULL);
+}
+
+static int cpu_ffa_notif_callback(struct notifier_block *nfb,
+ unsigned long action,
+ void *hcpu)
+{
+ switch ( action )
+ {
+ case CPU_DYING:
+ deinit_ffa_notif_interrupt();
+ break;
+ default:
+ /* Ignore other CPU events. */
+ break;
}
+
+ return NOTIFY_DONE;
}
+static struct notifier_block cpu_ffa_notif_nfb = {
+ .notifier_call = cpu_ffa_notif_callback,
+};
+
void ffa_notif_init(void)
{
const struct arm_smccc_1_2_regs arg = {
@@ -416,13 +457,11 @@ void ffa_notif_init(void)
return;
}
}
- ret = request_irq(irq, 0, notif_irq_handler, "FF-A notif", NULL);
- if ( ret )
- {
- printk(XENLOG_ERR "ffa: request_irq irq %u failed: error %d\n",
- irq, ret);
+
+ if ( request_sri_irq() )
return;
- }
+
+ register_cpu_notifier(&cpu_ffa_notif_nfb);
fw_notif_enabled = true;
}
}
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v14 09/15] iommu/ipmmu-vmsa: Implement suspend/resume callbacks
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (7 preceding siblings ...)
2026-11-17 1:04 ` [PATCH v14 08/15] xen/arm: ffa: fix notification SRI across CPU hotplug/suspend Mykola Kvach
@ 2026-11-17 1:04 ` Mykola Kvach
2026-11-17 1:05 ` [PATCH v14 10/15] xen/arm: smmu-v3: add suspend/resume handlers Mykola Kvach
` (5 subsequent siblings)
14 siblings, 0 replies; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:04 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk, Luca Fancellu
From: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Store and restore active context and micro-TLB registers.
On resume, restore Root IPMMU context state before restoring Cache IPMMU
micro-TLB state. Cache IPMMUs select Root contexts through their micro-TLB
configuration, so restoring Cache micro-TLBs before the Root context
registers are restored can expose stale or uninitialized context state.
Tested only on H3ULCB (R-Car Gen3).
Signed-off-by: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Luca Fancellu <luca.fancellu@arm.com>
Acked-by: Bertrand Marquis <bertrand.marquis@arm.com>
---
Changes in V13:
- State that suspend/resume was tested only on H3ULCB (R-Car Gen3).
Changes in V10:
- Iterate over registered IPMMUs in reverse order during resume so Root IPMMU
context state is restored before Cache IPMMU micro-TLB state.
Changes in V9:
- set dt_device_set_protected() only after ipmmu_alloc_ctx_suspend()
succeeds, so DT devices do not remain protected on allocation failure.
Changes in V7:
- moved suspend context allocation before pci stuff
---
xen/drivers/passthrough/arm/ipmmu-vmsa.c | 323 +++++++++++++++++++++--
1 file changed, 308 insertions(+), 15 deletions(-)
diff --git a/xen/drivers/passthrough/arm/ipmmu-vmsa.c b/xen/drivers/passthrough/arm/ipmmu-vmsa.c
index 0648f9b407..525dcfcea1 100644
--- a/xen/drivers/passthrough/arm/ipmmu-vmsa.c
+++ b/xen/drivers/passthrough/arm/ipmmu-vmsa.c
@@ -71,6 +71,8 @@
})
#endif
+#define dev_dbg(dev, fmt, ...) \
+ dev_print(dev, XENLOG_DEBUG, fmt, ## __VA_ARGS__)
#define dev_info(dev, fmt, ...) \
dev_print(dev, XENLOG_INFO, fmt, ## __VA_ARGS__)
#define dev_warn(dev, fmt, ...) \
@@ -130,6 +132,24 @@ struct ipmmu_features {
unsigned int imuctr_ttsel_mask;
};
+#ifdef CONFIG_SYSTEM_SUSPEND
+
+struct ipmmu_reg_ctx {
+ unsigned int imttlbr0;
+ unsigned int imttubr0;
+ unsigned int imttbcr;
+ unsigned int imctr;
+};
+
+struct ipmmu_vmsa_backup {
+ struct device *dev;
+ unsigned int *utlbs_val;
+ unsigned int *asids_val;
+ struct list_head list;
+};
+
+#endif
+
/* Root/Cache IPMMU device's information */
struct ipmmu_vmsa_device {
struct device *dev;
@@ -142,6 +162,9 @@ struct ipmmu_vmsa_device {
struct ipmmu_vmsa_domain *domains[IPMMU_CTX_MAX];
unsigned int utlb_refcount[IPMMU_UTLB_MAX];
const struct ipmmu_features *features;
+#ifdef CONFIG_SYSTEM_SUSPEND
+ struct ipmmu_reg_ctx *reg_backup[IPMMU_CTX_MAX];
+#endif
};
/*
@@ -547,6 +570,249 @@ static void ipmmu_domain_free_context(struct ipmmu_vmsa_device *mmu,
spin_unlock_irqrestore(&mmu->lock, flags);
}
+#ifdef CONFIG_SYSTEM_SUSPEND
+
+static DEFINE_SPINLOCK(ipmmu_devices_backup_lock);
+static LIST_HEAD(ipmmu_devices_backup);
+
+static struct ipmmu_reg_ctx root_pgtable[IPMMU_CTX_MAX];
+
+static uint32_t ipmmu_imuasid_read(struct ipmmu_vmsa_device *mmu,
+ unsigned int utlb)
+{
+ return ipmmu_read(mmu, ipmmu_utlb_reg(mmu, IMUASID(utlb)));
+}
+
+static void ipmmu_utlbs_backup(struct ipmmu_vmsa_device *mmu)
+{
+ struct ipmmu_vmsa_backup *backup_data;
+
+ dev_dbg(mmu->dev, "Handle micro-TLBs backup\n");
+
+ spin_lock(&ipmmu_devices_backup_lock);
+
+ list_for_each_entry( backup_data, &ipmmu_devices_backup, list )
+ {
+ struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(backup_data->dev);
+ unsigned int i;
+
+ if ( to_ipmmu(backup_data->dev) != mmu )
+ continue;
+
+ for ( i = 0; i < fwspec->num_ids; i++ )
+ {
+ unsigned int utlb = fwspec->ids[i];
+
+ backup_data->asids_val[i] = ipmmu_imuasid_read(mmu, utlb);
+ backup_data->utlbs_val[i] = ipmmu_imuctr_read(mmu, utlb);
+ }
+ }
+
+ spin_unlock(&ipmmu_devices_backup_lock);
+}
+
+static void ipmmu_utlbs_restore(struct ipmmu_vmsa_device *mmu)
+{
+ struct ipmmu_vmsa_backup *backup_data;
+
+ dev_dbg(mmu->dev, "Handle micro-TLBs restore\n");
+
+ spin_lock(&ipmmu_devices_backup_lock);
+
+ list_for_each_entry( backup_data, &ipmmu_devices_backup, list )
+ {
+ struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(backup_data->dev);
+ unsigned int i;
+
+ if ( to_ipmmu(backup_data->dev) != mmu )
+ continue;
+
+ for ( i = 0; i < fwspec->num_ids; i++ )
+ {
+ unsigned int utlb = fwspec->ids[i];
+
+ ipmmu_imuasid_write(mmu, utlb, backup_data->asids_val[i]);
+ ipmmu_imuctr_write(mmu, utlb, backup_data->utlbs_val[i]);
+ }
+ }
+
+ spin_unlock(&ipmmu_devices_backup_lock);
+}
+
+static void ipmmu_domain_backup_context(struct ipmmu_vmsa_domain *domain)
+{
+ struct ipmmu_vmsa_device *mmu = domain->mmu->root;
+ struct ipmmu_reg_ctx *regs = mmu->reg_backup[domain->context_id];
+
+ dev_dbg(mmu->dev, "Handle domain context %u backup\n", domain->context_id);
+
+ regs->imttlbr0 = ipmmu_ctx_read_root(domain, IMTTLBR0);
+ regs->imttubr0 = ipmmu_ctx_read_root(domain, IMTTUBR0);
+ regs->imttbcr = ipmmu_ctx_read_root(domain, IMTTBCR);
+ regs->imctr = ipmmu_ctx_read_root(domain, IMCTR);
+}
+
+static void ipmmu_domain_restore_context(struct ipmmu_vmsa_domain *domain)
+{
+ struct ipmmu_vmsa_device *mmu = domain->mmu->root;
+ struct ipmmu_reg_ctx *regs = mmu->reg_backup[domain->context_id];
+
+ dev_dbg(mmu->dev, "Handle domain context %u restore\n", domain->context_id);
+
+ ipmmu_ctx_write_root(domain, IMTTLBR0, regs->imttlbr0);
+ ipmmu_ctx_write_root(domain, IMTTUBR0, regs->imttubr0);
+ ipmmu_ctx_write_root(domain, IMTTBCR, regs->imttbcr);
+ ipmmu_ctx_write_all(domain, IMCTR, regs->imctr | IMCTR_FLUSH);
+}
+
+/*
+ * Xen: Unlike Linux implementation, Xen uses a single driver instance
+ * for handling all IPMMUs. There is no framework for ipmmu_suspend/resume
+ * callbacks to be invoked for each IPMMU device. So, we need to iterate
+ * through all registered IPMMUs performing required actions.
+ *
+ * Also take care of restoring special settings, such as translation
+ * table format, etc.
+ */
+static int __must_check ipmmu_suspend(void)
+{
+ struct ipmmu_vmsa_device *mmu;
+
+ if ( !iommu_enabled )
+ return 0;
+
+ printk(XENLOG_DEBUG "ipmmu: Suspending...\n");
+
+ spin_lock(&ipmmu_devices_lock);
+
+ list_for_each_entry( mmu, &ipmmu_devices, list )
+ {
+ if ( ipmmu_is_root(mmu) )
+ {
+ unsigned int i;
+
+ for ( i = 0; i < mmu->num_ctx; i++ )
+ {
+ if ( !mmu->domains[i] )
+ continue;
+ ipmmu_domain_backup_context(mmu->domains[i]);
+ }
+ }
+ else
+ ipmmu_utlbs_backup(mmu);
+ }
+
+ spin_unlock(&ipmmu_devices_lock);
+
+ return 0;
+}
+
+static void ipmmu_resume(void)
+{
+ struct ipmmu_vmsa_device *mmu;
+
+ if ( !iommu_enabled )
+ return;
+
+ printk(XENLOG_DEBUG "ipmmu: Resuming...\n");
+
+ spin_lock(&ipmmu_devices_lock);
+
+ /*
+ * IPMMUs are registered with list_add(), with Root IPMMU probed first.
+ * Walk backwards to restore Root contexts before Cache micro-TLBs.
+ */
+ list_for_each_entry_reverse( mmu, &ipmmu_devices, list )
+ {
+ uint32_t reg;
+
+ /* Do not use security group function */
+ reg = IMSCTLR + mmu->features->control_offset_base;
+ ipmmu_write(mmu, reg, ipmmu_read(mmu, reg) & ~IMSCTLR_USE_SECGRP);
+
+ if ( ipmmu_is_root(mmu) )
+ {
+ unsigned int i;
+
+ /* Use stage 2 translation table format */
+ reg = IMSAUXCTLR + mmu->features->control_offset_base;
+ ipmmu_write(mmu, reg, ipmmu_read(mmu, reg) | IMSAUXCTLR_S2PTE);
+
+ for ( i = 0; i < mmu->num_ctx; i++ )
+ {
+ if ( !mmu->domains[i] )
+ continue;
+ ipmmu_domain_restore_context(mmu->domains[i]);
+ }
+ }
+ else
+ ipmmu_utlbs_restore(mmu);
+ }
+
+ spin_unlock(&ipmmu_devices_lock);
+}
+
+static int ipmmu_alloc_ctx_suspend(struct device *dev)
+{
+ struct ipmmu_vmsa_backup *backup_data;
+ unsigned int *utlbs_val, *asids_val;
+ struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+
+ utlbs_val = xzalloc_array(unsigned int, fwspec->num_ids);
+ if ( !utlbs_val )
+ return -ENOMEM;
+
+ asids_val = xzalloc_array(unsigned int, fwspec->num_ids);
+ if ( !asids_val )
+ {
+ xfree(utlbs_val);
+ return -ENOMEM;
+ }
+
+ backup_data = xzalloc(struct ipmmu_vmsa_backup);
+ if ( !backup_data )
+ {
+ xfree(utlbs_val);
+ xfree(asids_val);
+ return -ENOMEM;
+ }
+
+ backup_data->dev = dev;
+ backup_data->utlbs_val = utlbs_val;
+ backup_data->asids_val = asids_val;
+
+ spin_lock(&ipmmu_devices_backup_lock);
+ list_add(&backup_data->list, &ipmmu_devices_backup);
+ spin_unlock(&ipmmu_devices_backup_lock);
+
+ return 0;
+}
+
+#ifdef CONFIG_HAS_PCI
+static void ipmmu_free_ctx_suspend(struct device *dev)
+{
+ struct ipmmu_vmsa_backup *backup_data, *tmp;
+
+ spin_lock(&ipmmu_devices_backup_lock);
+
+ list_for_each_entry_safe( backup_data, tmp, &ipmmu_devices_backup, list )
+ {
+ if ( backup_data->dev == dev )
+ {
+ list_del(&backup_data->list);
+ xfree(backup_data->utlbs_val);
+ xfree(backup_data->asids_val);
+ xfree(backup_data);
+ break;
+ }
+ }
+
+ spin_unlock(&ipmmu_devices_backup_lock);
+}
+#endif /* CONFIG_HAS_PCI */
+
+#endif /* CONFIG_SYSTEM_SUSPEND */
+
static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
{
uint64_t ttbr;
@@ -559,6 +825,9 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
return ret;
domain->context_id = ret;
+#ifdef CONFIG_SYSTEM_SUSPEND
+ domain->mmu->root->reg_backup[ret] = &root_pgtable[ret];
+#endif
/*
* TTBR0
@@ -615,6 +884,9 @@ static void ipmmu_domain_destroy_context(struct ipmmu_vmsa_domain *domain)
ipmmu_ctx_write_root(domain, IMCTR, IMCTR_FLUSH);
ipmmu_tlb_sync(domain);
+#ifdef CONFIG_SYSTEM_SUSPEND
+ domain->mmu->root->reg_backup[domain->context_id] = NULL;
+#endif
ipmmu_domain_free_context(domain->mmu->root, domain->context_id);
}
@@ -1338,10 +1610,11 @@ static int ipmmu_add_device(u8 devfn, struct device *dev)
struct iommu_fwspec *fwspec;
#ifdef CONFIG_HAS_PCI
+ int ret;
+
if ( dev_is_pci(dev) )
{
struct pci_dev *pdev = dev_to_pci(dev);
- int ret;
if ( devfn != pdev->devfn )
return 0;
@@ -1358,17 +1631,24 @@ static int ipmmu_add_device(u8 devfn, struct device *dev)
if ( !to_ipmmu(dev) )
return -ENODEV;
- if ( !dev_is_pci(dev) )
+ if ( !dev_is_pci(dev) && dt_device_is_protected(dev_to_dt(dev)) )
{
- if ( dt_device_is_protected(dev_to_dt(dev)) )
- {
- dev_err(dev, "Already added to IPMMU\n");
- return -EEXIST;
- }
+ dev_err(dev, "Already added to IPMMU\n");
+ return -EEXIST;
+ }
- /* Let Xen know that the master device is protected by an IOMMU. */
- dt_device_set_protected(dev_to_dt(dev), true);
+#ifdef CONFIG_SYSTEM_SUSPEND
+ if ( ipmmu_alloc_ctx_suspend(dev) )
+ {
+ dev_err(dev, "Failed to allocate context for suspend\n");
+ return -ENOMEM;
}
+#endif
+
+ /* Let Xen know that the master device is protected by an IOMMU. */
+ if ( !dev_is_pci(dev) )
+ dt_device_set_protected(dev_to_dt(dev), true);
+
#ifdef CONFIG_HAS_PCI
if ( dev_is_pci(dev) )
{
@@ -1377,26 +1657,28 @@ static int ipmmu_add_device(u8 devfn, struct device *dev)
struct pci_host_bridge *bridge;
struct iommu_fwspec *fwspec_bridge;
unsigned int utlb_osid0 = 0;
- int ret;
bridge = pci_find_host_bridge(pdev->seg, pdev->bus);
if ( !bridge )
{
dev_err(dev, "Failed to find host bridge\n");
- return -ENODEV;
+ ret = -ENODEV;
+ goto free_suspend_ctx;
}
fwspec_bridge = dev_iommu_fwspec_get(dt_to_dev(bridge->dt_node));
if ( fwspec_bridge->num_ids < 1 )
{
dev_err(dev, "Failed to find host bridge uTLB\n");
- return -ENXIO;
+ ret = -ENXIO;
+ goto free_suspend_ctx;
}
if ( fwspec->num_ids < 1 )
{
dev_err(dev, "Failed to find uTLB");
- return -ENXIO;
+ ret = -ENXIO;
+ goto free_suspend_ctx;
}
rcar4_pcie_osid_regs_init(bridge);
@@ -1405,7 +1687,7 @@ static int ipmmu_add_device(u8 devfn, struct device *dev)
if ( ret < 0 )
{
dev_err(dev, "No unused OSID regs\n");
- return ret;
+ goto free_suspend_ctx;
}
reg_id = ret;
@@ -1420,7 +1702,7 @@ static int ipmmu_add_device(u8 devfn, struct device *dev)
{
rcar4_pcie_osid_bdf_clear(bridge, reg_id);
rcar4_pcie_osid_reg_free(bridge, reg_id);
- return ret;
+ goto free_suspend_ctx;
}
}
#endif
@@ -1429,6 +1711,13 @@ static int ipmmu_add_device(u8 devfn, struct device *dev)
dev_name(fwspec->iommu_dev), fwspec->num_ids);
return 0;
+#ifdef CONFIG_HAS_PCI
+ free_suspend_ctx:
+#ifdef CONFIG_SYSTEM_SUSPEND
+ ipmmu_free_ctx_suspend(dev);
+#endif
+ return ret;
+#endif
}
static int ipmmu_iommu_domain_init(struct domain *d)
@@ -1490,6 +1779,10 @@ static const struct iommu_ops ipmmu_iommu_ops =
.unmap_page = arm_iommu_unmap_page,
.dt_xlate = ipmmu_dt_xlate,
.add_device = ipmmu_add_device,
+#ifdef CONFIG_SYSTEM_SUSPEND
+ .suspend = ipmmu_suspend,
+ .resume = ipmmu_resume,
+#endif
};
static __init int ipmmu_init(struct dt_device_node *node, const void *data)
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v14 10/15] xen/arm: smmu-v3: add suspend/resume handlers
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (8 preceding siblings ...)
2026-11-17 1:04 ` [PATCH v14 09/15] iommu/ipmmu-vmsa: Implement suspend/resume callbacks Mykola Kvach
@ 2026-11-17 1:05 ` Mykola Kvach
2026-11-17 17:04 ` Bertrand Marquis
2026-11-17 1:05 ` [PATCH v14 11/15] xen/arm64: Keep the early UART message in the identity mapping Mykola Kvach
` (4 subsequent siblings)
14 siblings, 1 reply; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:05 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Bertrand Marquis, Rahul Singh, Stefano Stabellini,
Julien Grall, Michal Orzel, Volodymyr Babchuk,
Pranjal Shrivastava
Add system suspend/resume callbacks for the Arm SMMUv3 driver.
During suspend, set GBPA.ABORT and disable the translation interface and
EVTQ/PRIQ, while keeping CMDQ enabled. Save the queue producer indices after
the disable acknowledgements, then issue CMD_SYNC to wait for all earlier
commands to complete. Disable interrupt generation before stopping CMDQ,
and handle any remaining global errors before the SMMU loses power.
If the initial GBPA update fails, leave that SMMU enabled and restore only
the previously suspended devices. For later failures, restore the current
SMMU as well. Before each rollback reset, wait for EVTQ/PRIQ to stop and
save their producer indices. This also covers a CR0ACK timeout before the
normal suspend path has saved the indices. Failure to stop the queues or
to reset during rollback is fatal, since the host suspend error path
allows domains to run again. Check GBPA and CMD_SYNC errors in reset so
an incomplete restore is not reported as successful.
Resume uses arm_smmu_device_reset() to restore the SMMU registers and queue
indices, invalidate cached configuration and translations, and enable the
SMMU. Always schedule the EVTQ tasklet on resume to refresh the hardware
producer index, including when the saved indices indicate an empty queue.
Re-enabling interrupts does not report events recorded before the interrupt
source was enabled. Prevent pending GERROR interrupts from accessing CMDQ
while it is reset.
Probe also changes with CONFIG_SYSTEM_SUSPEND disabled. Request IRQ
handlers only after the queues and tasklets are ready. If reset fails
during probe, call arm_smmu_device_disable() before freeing resources,
since queues may already be enabled. Panic if disabling fails: the SMMU
may still access the queue memory. The GERROR guard is also compiled in,
but is cleared before handlers are registered and stays clear after probe.
Reset now returns GBPA and CMD_SYNC errors in these builds too.
Clear MSI target addresses on both probe and resume, also without
CONFIG_MSI. Arm IHI0070G.b, sections 6.3.21 and 6.3.30, specify that these
addresses reset to UNKNOWN and that zero disables MSIs while allowing
wired IRQs. The corresponding IRQ_CTRL and IRQ_CTRLACK enable bits must
both be clear before writing these registers. Disable interrupt generation
and wait for IRQ_CTRLACK, as described in section 6.3.16, before clearing
the addresses.
Xen currently does not support SMMUv3 MSI interrupts or PCI ATS/PRI. Active
MSI configuration restore and ATS/PRI endpoint suspend handling remain
outside this patch.
Link: https://lore.kernel.org/r/20260929034510.2023173-1-praan@google.com/
Based-on-patch-by: Pranjal Shrivastava <praan@google.com>
Assisted-by: Codex:GPT-6
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
---
Changes in V14:
- Schedule the EVTQ tasklet unconditionally on resume so it refreshes
the hardware producer index even when the saved indices indicate an
empty queue.
Changes in V13:
- Rename __init_or_smmu_suspend to init_or_smmu_suspend to avoid a reserved
macro name (MISRA Rule 21.1). No functional change.
- Check arm_smmu_device_disable() after a probe reset failure (MISRA Rule
17.7). Panic if disabling fails, before freeing queue memory.
- Adapt the relevant fixes from v11 of the Linux SMMUv3 suspend series.
- Request IRQs after the queues and tasklets are ready, only during probe.
- Disable the SMMU on probe-time reset failure before freeing resources.
- Check GBPA and CMD_SYNC errors in reset, and make a failed rollback reset
fatal before the host suspend error path can resume domain execution.
- Leave the current SMMU enabled if the initial GBPA update fails; restore
only the previously suspended devices.
- Clear MSI target addresses on probe and resume, also when using wired
IRQs, and document the register requirements from IHI0070G.b.
- Save EVTQ/PRIQ producer indices after confirming that the queues have
stopped, both during suspend and before rollback reset. Cover a CR0ACK
timeout before the normal snapshot. Schedule tasklets after reset to
process unread entries without waiting for a new interrupt.
- Keep GERROR handling available until interrupt generation is disabled,
then gate its IRQ handler before stopping CMDQ. Handle remaining global
errors before power-off and allow the handler again once CMDQ is restored.
- Drop Luca's Reviewed-by tag because the patch has changed.
Changes in V11:
- Keep arm_smmu_update_gbpa() and arm_smmu_device_reset() in init text when
CONFIG_SYSTEM_SUSPEND is disabled.
Changes in V10:
- Disable SMMU interrupt generation during suspend before disabling the
SMMU interface, matching the resume/reset path which re-enables IRQ_CTRL.
Changes in V9:
- Use CMD_SYNC in suspend instead of polling CMDQ_CONS, so the suspend
path waits for command completion rather than only command consumption.
- Document that arm_smmu_setup_irqs() is probe-only and that future Xen
SMMUv3 MSI support will need to restore SMMU IRQ_CFGn registers on
resume.
- Restore the reference to Pranjal's Linux runtime/system sleep series and
clarify that MSI/ATS/PRI resume handling is outside the supported Xen
path.
- Prefix the subject with xen/arm for consistency with the rest of the
Arm suspend/resume series.
Changes in V8:
- Honor ARM_SMMU_FEAT_SEV when draining the CMDQ during suspend, matching
the existing runtime CMD_SYNC path.
- Fold the suspend rollback reset path into a helper and rename the error
reporting to describe suspend rollback rather than resume.
- Treat SMMU reset failure during resume as fatal instead of logging and
continuing with a potentially unusable IOMMU.
- cosmetic changes
---
xen/drivers/passthrough/arm/smmu-v3.c | 308 +++++++++++++++++++++-----
xen/drivers/passthrough/arm/smmu-v3.h | 1 +
2 files changed, 258 insertions(+), 51 deletions(-)
diff --git a/xen/drivers/passthrough/arm/smmu-v3.c b/xen/drivers/passthrough/arm/smmu-v3.c
index 232df2421c..fa0c57886e 100644
--- a/xen/drivers/passthrough/arm/smmu-v3.c
+++ b/xen/drivers/passthrough/arm/smmu-v3.c
@@ -94,6 +94,12 @@
#include "smmu-v3.h"
+#ifdef CONFIG_SYSTEM_SUSPEND
+#define init_or_smmu_suspend
+#else
+#define init_or_smmu_suspend __init
+#endif
+
#define ARM_SMMU_VTCR_SH_IS 3
#define ARM_SMMU_VTCR_RGN_WBWA 1
#define ARM_SMMU_VTCR_TG0_4K 0
@@ -903,10 +909,10 @@ static void arm_smmu_priq_tasklet(void *dev)
static int arm_smmu_device_disable(struct arm_smmu_device *smmu);
-static void arm_smmu_gerror_handler(int irq, void *dev)
+/* The caller must serialize with the IRQ handler. */
+static void arm_smmu_handle_gerror(struct arm_smmu_device *smmu)
{
u32 gerror, gerrorn, active;
- struct arm_smmu_device *smmu = dev;
gerror = readl_relaxed(smmu->base + ARM_SMMU_GERROR);
gerrorn = readl_relaxed(smmu->base + ARM_SMMU_GERRORN);
@@ -948,6 +954,14 @@ static void arm_smmu_gerror_handler(int irq, void *dev)
writel(gerror, smmu->base + ARM_SMMU_GERRORN);
}
+static void arm_smmu_gerror_handler(int irq, void *dev)
+{
+ struct arm_smmu_device *smmu = dev;
+
+ if (!read_atomic(&smmu->gerror_blocked))
+ arm_smmu_handle_gerror(smmu);
+}
+
static void arm_smmu_combined_irq_handler(int irq, void *dev)
{
struct arm_smmu_device *smmu = dev;
@@ -1871,8 +1885,8 @@ static int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
}
/* GBPA is "special" */
-static int __init arm_smmu_update_gbpa(struct arm_smmu_device *smmu,
- u32 set, u32 clr)
+static int init_or_smmu_suspend
+arm_smmu_update_gbpa(struct arm_smmu_device *smmu, u32 set, u32 clr)
{
int ret;
u32 reg, __iomem *gbpa = smmu->base + ARM_SMMU_GBPA;
@@ -1893,6 +1907,20 @@ static int __init arm_smmu_update_gbpa(struct arm_smmu_device *smmu,
return ret;
}
+static void arm_smmu_clear_msi_cfg(struct arm_smmu_device *smmu)
+{
+ /*
+ * IHI0070G.b, sections 6.3.21 and 6.3.30: ADDR resets to UNKNOWN.
+ * ADDR == 0 disables MSIs while allowing wired IRQs. The corresponding
+ * IRQ_CTRL and IRQ_CTRLACK enable bits must be clear before writing.
+ */
+ writeq_relaxed(0, smmu->base + ARM_SMMU_GERROR_IRQ_CFG0);
+ writeq_relaxed(0, smmu->base + ARM_SMMU_EVTQ_IRQ_CFG0);
+
+ if (smmu->features & ARM_SMMU_FEAT_PRI)
+ writeq_relaxed(0, smmu->base + ARM_SMMU_PRIQ_IRQ_CFG0);
+}
+
#ifdef CONFIG_MSI
static void arm_smmu_free_msis(void *data)
{
@@ -1921,13 +1949,7 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
int ret, nvec = ARM_SMMU_MAX_MSIS;
struct device *dev = smmu->dev;
- /* Clear the MSI address regs */
- writeq_relaxed(0, smmu->base + ARM_SMMU_GERROR_IRQ_CFG0);
- writeq_relaxed(0, smmu->base + ARM_SMMU_EVTQ_IRQ_CFG0);
-
- if (smmu->features & ARM_SMMU_FEAT_PRI)
- writeq_relaxed(0, smmu->base + ARM_SMMU_PRIQ_IRQ_CFG0);
- else
+ if (!(smmu->features & ARM_SMMU_FEAT_PRI))
nvec--;
if (!(smmu->features & ARM_SMMU_FEAT_MSI))
@@ -1968,7 +1990,8 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
static inline void arm_smmu_setup_msis(struct arm_smmu_device *smmu) { }
#endif /* CONFIG_MSI */
-static void __init arm_smmu_free_irqs(struct arm_smmu_device *smmu)
+static void init_or_smmu_suspend
+arm_smmu_free_irqs(struct arm_smmu_device *smmu)
{
int irq;
@@ -2052,19 +2075,38 @@ err_free_evtq_irq:
return ret;
}
-static int __init arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
+static int arm_smmu_enable_irqs(struct arm_smmu_device *smmu)
{
- int ret, irq;
+ int ret;
u32 irqen_flags = IRQ_CTRL_EVTQ_IRQEN | IRQ_CTRL_GERROR_IRQEN;
- /* Disable IRQs first */
- ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_IRQ_CTRL,
- ARM_SMMU_IRQ_CTRLACK);
- if (ret) {
- dev_err(smmu->dev, "failed to disable irqs\n");
+ if ( smmu->features & ARM_SMMU_FEAT_PRI )
+ irqen_flags |= IRQ_CTRL_PRIQ_IRQEN;
+
+ /* Enable interrupt generation on the SMMU */
+ ret = arm_smmu_write_reg_sync(smmu, irqen_flags,
+ ARM_SMMU_IRQ_CTRL, ARM_SMMU_IRQ_CTRLACK);
+ if ( ret )
+ {
+ dev_warn(smmu->dev, "failed to enable irqs\n");
return ret;
}
+ return 0;
+}
+
+static int arm_smmu_disable_irqs(struct arm_smmu_device *smmu)
+{
+ return arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_IRQ_CTRL,
+ ARM_SMMU_IRQ_CTRLACK);
+}
+
+/* Probe-time only; reset has configured the queues and disabled IRQs. */
+static int init_or_smmu_suspend
+arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
+{
+ int ret, irq;
+
irq = smmu->combined_irq;
if (irq) {
/*
@@ -2085,22 +2127,7 @@ static int __init arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
}
}
- if (smmu->features & ARM_SMMU_FEAT_PRI)
- irqen_flags |= IRQ_CTRL_PRIQ_IRQEN;
-
- /* Enable interrupt generation on the SMMU */
- ret = arm_smmu_write_reg_sync(smmu, irqen_flags,
- ARM_SMMU_IRQ_CTRL, ARM_SMMU_IRQ_CTRLACK);
- if (ret) {
- dev_warn(smmu->dev, "failed to enable irqs\n");
- goto err_free_irqs;
- }
-
return 0;
-
-err_free_irqs:
- arm_smmu_free_irqs(smmu);
- return ret;
}
static int arm_smmu_device_disable(struct arm_smmu_device *smmu)
@@ -2114,18 +2141,31 @@ static int arm_smmu_device_disable(struct arm_smmu_device *smmu)
return ret;
}
-static int __init arm_smmu_device_reset(struct arm_smmu_device *smmu)
+static int init_or_smmu_suspend
+arm_smmu_device_reset(struct arm_smmu_device *smmu, bool resume)
{
int ret;
u32 reg, enables;
struct arm_smmu_cmdq_ent cmd;
+ ret = arm_smmu_disable_irqs(smmu);
+ if (ret) {
+ dev_err(smmu->dev, "failed to disable irqs\n");
+ return ret;
+ }
+
+ /* A pending GERROR IRQ must not access CMDQ while it is reset. */
+ write_atomic(&smmu->gerror_blocked, true);
+ arm_smmu_clear_msi_cfg(smmu);
+
/* Clear CR0 and sync (disables SMMU and queue processing) */
reg = readl_relaxed(smmu->base + ARM_SMMU_CR0);
if (reg & CR0_SMMUEN) {
dev_warn(smmu->dev, "SMMU currently enabled! Resetting...\n");
WARN_ON(!disable_bypass);
- arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0);
+ ret = arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0);
+ if (ret)
+ return ret;
}
ret = arm_smmu_device_disable(smmu);
@@ -2164,10 +2204,15 @@ static int __init arm_smmu_device_reset(struct arm_smmu_device *smmu)
return ret;
}
+ /* GERROR handling can use CMDQ again once its registers are restored. */
+ write_atomic(&smmu->gerror_blocked, false);
+
/* Invalidate any cached configuration */
cmd.opcode = CMDQ_OP_CFGI_ALL;
arm_smmu_cmdq_issue_cmd(smmu, &cmd);
- arm_smmu_cmdq_issue_sync(smmu);
+ ret = arm_smmu_cmdq_issue_sync(smmu);
+ if (ret)
+ return ret;
/* Invalidate any stale TLB entries */
if (smmu->features & ARM_SMMU_FEAT_HYP) {
@@ -2177,7 +2222,9 @@ static int __init arm_smmu_device_reset(struct arm_smmu_device *smmu)
cmd.opcode = CMDQ_OP_TLBI_NSNH_ALL;
arm_smmu_cmdq_issue_cmd(smmu, &cmd);
- arm_smmu_cmdq_issue_sync(smmu);
+ ret = arm_smmu_cmdq_issue_sync(smmu);
+ if (ret)
+ return ret;
/* Event queue */
writeq_relaxed(smmu->evtq.q.q_base, smmu->base + ARM_SMMU_EVTQ_BASE);
@@ -2220,17 +2267,18 @@ static int __init arm_smmu_device_reset(struct arm_smmu_device *smmu)
}
}
- ret = arm_smmu_setup_irqs(smmu);
- if (ret) {
- dev_err(smmu->dev, "failed to setup irqs\n");
- return ret;
+ /* Register handlers only after their queues and tasklets are ready. */
+ if (!resume) {
+ ret = arm_smmu_setup_irqs(smmu);
+ if (ret) {
+ dev_err(smmu->dev, "failed to setup irqs\n");
+ return ret;
+ }
}
- /* Initialize tasklets for threaded IRQs*/
- tasklet_init(&smmu->evtq_irq_tasklet, arm_smmu_evtq_tasklet, smmu);
- tasklet_init(&smmu->priq_irq_tasklet, arm_smmu_priq_tasklet, smmu);
- tasklet_init(&smmu->combined_irq_tasklet, arm_smmu_combined_irq_tasklet,
- smmu);
+ ret = arm_smmu_enable_irqs(smmu);
+ if (ret)
+ goto err_free_irqs;
/* Enable the SMMU interface, or ensure bypass */
if (disable_bypass) {
@@ -2247,10 +2295,18 @@ static int __init arm_smmu_device_reset(struct arm_smmu_device *smmu)
goto err_free_irqs;
}
+ /* IHI0070G.b, section 6.3.16: re-enabling IRQs does not replay events. */
+ if (resume)
+ tasklet_schedule(&smmu->evtq_irq_tasklet);
+ if (resume && (smmu->features & ARM_SMMU_FEAT_PRI) &&
+ !queue_empty(&smmu->priq.q.llq))
+ tasklet_schedule(&smmu->priq_irq_tasklet);
+
return 0;
err_free_irqs:
- arm_smmu_free_irqs(smmu);
+ if (!resume)
+ arm_smmu_free_irqs(smmu);
return ret;
}
@@ -2615,10 +2671,21 @@ static int __init arm_smmu_device_probe(struct platform_device *pdev)
if (ret)
goto out_free;
+ /* Initialize tasklets for threaded IRQs*/
+ tasklet_init(&smmu->evtq_irq_tasklet, arm_smmu_evtq_tasklet, smmu);
+ tasklet_init(&smmu->priq_irq_tasklet, arm_smmu_priq_tasklet, smmu);
+ tasklet_init(&smmu->combined_irq_tasklet, arm_smmu_combined_irq_tasklet,
+ smmu);
+
/* Reset the device */
- ret = arm_smmu_device_reset(smmu);
- if (ret)
+ ret = arm_smmu_device_reset(smmu, false);
+ if (ret) {
+ /* Reset may have enabled queues before failing. */
+ if (arm_smmu_device_disable(smmu))
+ panic("SMMUv3: %s: Failed to disable during probe cleanup\n",
+ dev_name(smmu->dev));
goto out_free;
+ }
/*
* Keep a list of all probed devices. This will be used to query
@@ -2632,7 +2699,6 @@ static int __init arm_smmu_device_probe(struct platform_device *pdev)
return 0;
-
out_free:
arm_smmu_free_structures(smmu);
if (smmu->page1)
@@ -2912,6 +2978,142 @@ static void arm_smmu_iommu_xen_domain_teardown(struct domain *d)
xfree(xen_domain);
}
+#ifdef CONFIG_SYSTEM_SUSPEND
+
+static void arm_smmu_save_queue_producers(struct arm_smmu_device *smmu)
+{
+ /*
+ * IHI0070G.b, sections 6.3.9.4 and 6.3.9.5: EVTQ/PRIQ disable
+ * acknowledgements make committed entries visible. The caller must
+ * wait for these acknowledgements before reading the producer indices.
+ */
+ if (queue_sync_prod_in(&smmu->evtq.q) == -EOVERFLOW)
+ dev_warn(smmu->dev, "EVTQ overflow detected during suspend\n");
+ if ((smmu->features & ARM_SMMU_FEAT_PRI) &&
+ queue_sync_prod_in(&smmu->priq.q) == -EOVERFLOW)
+ dev_warn(smmu->dev, "PRIQ overflow detected during suspend\n");
+}
+
+static void arm_smmu_reset_for_suspend_rollback(struct arm_smmu_device *smmu)
+{
+ int ret;
+ u32 reg;
+
+ /*
+ * The queues have been requested to stop, but a CR0ACK timeout may
+ * have skipped saving their producer indices. Wait for the queue
+ * disable acknowledgements before reset overwrites those indices.
+ */
+ ret = readl_relaxed_poll_timeout(smmu->base + ARM_SMMU_CR0ACK, reg,
+ !(reg & (CR0_EVTQEN | CR0_PRIQEN)),
+ 1, ARM_SMMU_POLL_TIMEOUT_US);
+ if (ret)
+ panic("SMMUv3: %s: Queue stop timed out during rollback: %d\n",
+ dev_name(smmu->dev), ret);
+
+ arm_smmu_save_queue_producers(smmu);
+ ret = arm_smmu_device_reset(smmu, true);
+
+ /* The host suspend error path allows domains to run again. */
+ if ( ret )
+ panic("SMMUv3: %s: Failed to reset during suspend rollback: %d\n",
+ dev_name(smmu->dev), ret);
+}
+
+static int arm_smmu_suspend(void)
+{
+ struct arm_smmu_device *smmu;
+ int ret = 0;
+
+ list_for_each_entry(smmu, &arm_smmu_devices, devices)
+ {
+ /* Abort all transactions before disable to avoid spurious bypass */
+ ret = arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0);
+ if ( ret )
+ goto rollback_previous;
+
+ /* Disable the SMMU via CR0.EN and all queues except CMDQ */
+ ret = arm_smmu_write_reg_sync(smmu, CR0_CMDQEN, ARM_SMMU_CR0,
+ ARM_SMMU_CR0ACK);
+ if ( ret )
+ {
+ dev_err(smmu->dev, "Timed-out while disabling smmu\n");
+ goto fail;
+ }
+
+ arm_smmu_save_queue_producers(smmu);
+
+ /*
+ * At this point the translation interface is disabled and the
+ * SMMU won't access translation/config structures, even
+ * speculatively, as per the IHI0070 spec (section 6.3.9.6).
+ * CMDQ is still enabled so that a CMD_SYNC can complete any
+ * previously issued commands.
+ */
+
+ /* Ensure all previously issued commands have completed. */
+ ret = arm_smmu_cmdq_issue_sync(smmu);
+ if ( ret )
+ {
+ dev_err(smmu->dev, "Timed-out waiting for pending commands\n");
+ goto fail;
+ }
+
+ /* Stop IRQ generation before gating the handler and disabling CMDQ. */
+ ret = arm_smmu_disable_irqs(smmu);
+ if (ret) {
+ dev_err(smmu->dev, "Timed-out while disabling SMMU irqs\n");
+ goto fail;
+ }
+ write_atomic(&smmu->gerror_blocked, true);
+
+ /* Disable everything */
+ ret = arm_smmu_device_disable(smmu);
+ if ( ret )
+ goto fail;
+
+ /* Other CPUs are offline and the IRQ handler is gated above. */
+ arm_smmu_handle_gerror(smmu);
+
+ dev_dbg(smmu->dev, "Suspended smmu\n");
+ }
+
+ return 0;
+
+ fail:
+ /* Reset the device that failed as well as any already-suspended ones. */
+ arm_smmu_reset_for_suspend_rollback(smmu);
+
+ rollback_previous:
+ /* An initial GBPA failure leaves this SMMU enabled: do not reset it. */
+ list_for_each_entry_continue_reverse(smmu, &arm_smmu_devices, devices)
+ arm_smmu_reset_for_suspend_rollback(smmu);
+
+ return ret;
+}
+
+static void arm_smmu_resume(void)
+{
+ int ret;
+ struct arm_smmu_device *smmu;
+
+ list_for_each_entry(smmu, &arm_smmu_devices, devices)
+ {
+ dev_dbg(smmu->dev, "Resuming device\n");
+
+ /*
+ * The reset will re-initialize all the base addresses, queues,
+ * prod and cons maintained within struct arm_smmu_device as well as
+ * re-enable the interrupts.
+ */
+ ret = arm_smmu_device_reset(smmu, true);
+ if ( ret )
+ panic("SMMUv3: %s: Failed to reset during resume: %d\n",
+ dev_name(smmu->dev), ret);
+ }
+}
+#endif
+
static const struct iommu_ops arm_smmu_iommu_ops = {
.page_sizes = PAGE_SIZE_4K,
.init = arm_smmu_iommu_xen_domain_init,
@@ -2925,6 +3127,10 @@ static const struct iommu_ops arm_smmu_iommu_ops = {
.dt_xlate = arm_smmu_dt_xlate,
.add_device = arm_smmu_add_device,
.remove_device = arm_smmu_remove_device,
+#ifdef CONFIG_SYSTEM_SUSPEND
+ .suspend = arm_smmu_suspend,
+ .resume = arm_smmu_resume,
+#endif
};
static __init int arm_smmu_dt_init(struct dt_device_node *dev,
diff --git a/xen/drivers/passthrough/arm/smmu-v3.h b/xen/drivers/passthrough/arm/smmu-v3.h
index ab07366294..93986886f2 100644
--- a/xen/drivers/passthrough/arm/smmu-v3.h
+++ b/xen/drivers/passthrough/arm/smmu-v3.h
@@ -613,6 +613,7 @@ struct arm_smmu_device {
int combined_irq;
u32 sync_nr;
u8 prev_cmd_opcode;
+ bool gerror_blocked;
unsigned long ias; /* IPA */
unsigned long oas; /* PA */
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* Re: [PATCH v14 10/15] xen/arm: smmu-v3: add suspend/resume handlers
2026-11-17 1:05 ` [PATCH v14 10/15] xen/arm: smmu-v3: add suspend/resume handlers Mykola Kvach
@ 2026-11-17 17:04 ` Bertrand Marquis
0 siblings, 0 replies; 20+ messages in thread
From: Bertrand Marquis @ 2026-11-17 17:04 UTC (permalink / raw)
To: Mykola Kvach
Cc: xen-devel@lists.xenproject.org, Rahul Singh, Stefano Stabellini,
Julien Grall, Michal Orzel, Volodymyr Babchuk,
Pranjal Shrivastava
Hi Mykola,
> On 17 Nov 2026, at 02:05, Mykola Kvach <mykola_kvach@epam.com> wrote:
>
> Add system suspend/resume callbacks for the Arm SMMUv3 driver.
>
> During suspend, set GBPA.ABORT and disable the translation interface and
> EVTQ/PRIQ, while keeping CMDQ enabled. Save the queue producer indices after
> the disable acknowledgements, then issue CMD_SYNC to wait for all earlier
> commands to complete. Disable interrupt generation before stopping CMDQ,
> and handle any remaining global errors before the SMMU loses power.
>
> If the initial GBPA update fails, leave that SMMU enabled and restore only
> the previously suspended devices. For later failures, restore the current
> SMMU as well. Before each rollback reset, wait for EVTQ/PRIQ to stop and
> save their producer indices. This also covers a CR0ACK timeout before the
> normal suspend path has saved the indices. Failure to stop the queues or
> to reset during rollback is fatal, since the host suspend error path
> allows domains to run again. Check GBPA and CMD_SYNC errors in reset so
> an incomplete restore is not reported as successful.
>
> Resume uses arm_smmu_device_reset() to restore the SMMU registers and queue
> indices, invalidate cached configuration and translations, and enable the
> SMMU. Always schedule the EVTQ tasklet on resume to refresh the hardware
> producer index, including when the saved indices indicate an empty queue.
> Re-enabling interrupts does not report events recorded before the interrupt
> source was enabled. Prevent pending GERROR interrupts from accessing CMDQ
> while it is reset.
>
> Probe also changes with CONFIG_SYSTEM_SUSPEND disabled. Request IRQ
> handlers only after the queues and tasklets are ready. If reset fails
> during probe, call arm_smmu_device_disable() before freeing resources,
> since queues may already be enabled. Panic if disabling fails: the SMMU
> may still access the queue memory. The GERROR guard is also compiled in,
> but is cleared before handlers are registered and stays clear after probe.
> Reset now returns GBPA and CMD_SYNC errors in these builds too.
>
> Clear MSI target addresses on both probe and resume, also without
> CONFIG_MSI. Arm IHI0070G.b, sections 6.3.21 and 6.3.30, specify that these
> addresses reset to UNKNOWN and that zero disables MSIs while allowing
> wired IRQs. The corresponding IRQ_CTRL and IRQ_CTRLACK enable bits must
> both be clear before writing these registers. Disable interrupt generation
> and wait for IRQ_CTRLACK, as described in section 6.3.16, before clearing
> the addresses.
>
> Xen currently does not support SMMUv3 MSI interrupts or PCI ATS/PRI. Active
> MSI configuration restore and ATS/PRI endpoint suspend handling remain
> outside this patch.
>
> Link: https://lore.kernel.org/r/20260929034510.2023173-1-praan@google.com/
> Based-on-patch-by: Pranjal Shrivastava <praan@google.com>
> Assisted-by: Codex:GPT-6
> Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
Cheers
Bertrand
> ---
> Changes in V14:
> - Schedule the EVTQ tasklet unconditionally on resume so it refreshes
> the hardware producer index even when the saved indices indicate an
> empty queue.
>
> Changes in V13:
> - Rename __init_or_smmu_suspend to init_or_smmu_suspend to avoid a reserved
> macro name (MISRA Rule 21.1). No functional change.
> - Check arm_smmu_device_disable() after a probe reset failure (MISRA Rule
> 17.7). Panic if disabling fails, before freeing queue memory.
> - Adapt the relevant fixes from v11 of the Linux SMMUv3 suspend series.
> - Request IRQs after the queues and tasklets are ready, only during probe.
> - Disable the SMMU on probe-time reset failure before freeing resources.
> - Check GBPA and CMD_SYNC errors in reset, and make a failed rollback reset
> fatal before the host suspend error path can resume domain execution.
> - Leave the current SMMU enabled if the initial GBPA update fails; restore
> only the previously suspended devices.
> - Clear MSI target addresses on probe and resume, also when using wired
> IRQs, and document the register requirements from IHI0070G.b.
> - Save EVTQ/PRIQ producer indices after confirming that the queues have
> stopped, both during suspend and before rollback reset. Cover a CR0ACK
> timeout before the normal snapshot. Schedule tasklets after reset to
> process unread entries without waiting for a new interrupt.
> - Keep GERROR handling available until interrupt generation is disabled,
> then gate its IRQ handler before stopping CMDQ. Handle remaining global
> errors before power-off and allow the handler again once CMDQ is restored.
> - Drop Luca's Reviewed-by tag because the patch has changed.
>
> Changes in V11:
> - Keep arm_smmu_update_gbpa() and arm_smmu_device_reset() in init text when
> CONFIG_SYSTEM_SUSPEND is disabled.
>
> Changes in V10:
> - Disable SMMU interrupt generation during suspend before disabling the
> SMMU interface, matching the resume/reset path which re-enables IRQ_CTRL.
>
> Changes in V9:
> - Use CMD_SYNC in suspend instead of polling CMDQ_CONS, so the suspend
> path waits for command completion rather than only command consumption.
> - Document that arm_smmu_setup_irqs() is probe-only and that future Xen
> SMMUv3 MSI support will need to restore SMMU IRQ_CFGn registers on
> resume.
> - Restore the reference to Pranjal's Linux runtime/system sleep series and
> clarify that MSI/ATS/PRI resume handling is outside the supported Xen
> path.
> - Prefix the subject with xen/arm for consistency with the rest of the
> Arm suspend/resume series.
>
> Changes in V8:
> - Honor ARM_SMMU_FEAT_SEV when draining the CMDQ during suspend, matching
> the existing runtime CMD_SYNC path.
> - Fold the suspend rollback reset path into a helper and rename the error
> reporting to describe suspend rollback rather than resume.
> - Treat SMMU reset failure during resume as fatal instead of logging and
> continuing with a potentially unusable IOMMU.
> - cosmetic changes
> ---
> xen/drivers/passthrough/arm/smmu-v3.c | 308 +++++++++++++++++++++-----
> xen/drivers/passthrough/arm/smmu-v3.h | 1 +
> 2 files changed, 258 insertions(+), 51 deletions(-)
>
> diff --git a/xen/drivers/passthrough/arm/smmu-v3.c b/xen/drivers/passthrough/arm/smmu-v3.c
> index 232df2421c..fa0c57886e 100644
> --- a/xen/drivers/passthrough/arm/smmu-v3.c
> +++ b/xen/drivers/passthrough/arm/smmu-v3.c
> @@ -94,6 +94,12 @@
>
> #include "smmu-v3.h"
>
> +#ifdef CONFIG_SYSTEM_SUSPEND
> +#define init_or_smmu_suspend
> +#else
> +#define init_or_smmu_suspend __init
> +#endif
> +
> #define ARM_SMMU_VTCR_SH_IS 3
> #define ARM_SMMU_VTCR_RGN_WBWA 1
> #define ARM_SMMU_VTCR_TG0_4K 0
> @@ -903,10 +909,10 @@ static void arm_smmu_priq_tasklet(void *dev)
>
> static int arm_smmu_device_disable(struct arm_smmu_device *smmu);
>
> -static void arm_smmu_gerror_handler(int irq, void *dev)
> +/* The caller must serialize with the IRQ handler. */
> +static void arm_smmu_handle_gerror(struct arm_smmu_device *smmu)
> {
> u32 gerror, gerrorn, active;
> - struct arm_smmu_device *smmu = dev;
>
> gerror = readl_relaxed(smmu->base + ARM_SMMU_GERROR);
> gerrorn = readl_relaxed(smmu->base + ARM_SMMU_GERRORN);
> @@ -948,6 +954,14 @@ static void arm_smmu_gerror_handler(int irq, void *dev)
> writel(gerror, smmu->base + ARM_SMMU_GERRORN);
> }
>
> +static void arm_smmu_gerror_handler(int irq, void *dev)
> +{
> + struct arm_smmu_device *smmu = dev;
> +
> + if (!read_atomic(&smmu->gerror_blocked))
> + arm_smmu_handle_gerror(smmu);
> +}
> +
> static void arm_smmu_combined_irq_handler(int irq, void *dev)
> {
> struct arm_smmu_device *smmu = dev;
> @@ -1871,8 +1885,8 @@ static int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
> }
>
> /* GBPA is "special" */
> -static int __init arm_smmu_update_gbpa(struct arm_smmu_device *smmu,
> - u32 set, u32 clr)
> +static int init_or_smmu_suspend
> +arm_smmu_update_gbpa(struct arm_smmu_device *smmu, u32 set, u32 clr)
> {
> int ret;
> u32 reg, __iomem *gbpa = smmu->base + ARM_SMMU_GBPA;
> @@ -1893,6 +1907,20 @@ static int __init arm_smmu_update_gbpa(struct arm_smmu_device *smmu,
> return ret;
> }
>
> +static void arm_smmu_clear_msi_cfg(struct arm_smmu_device *smmu)
> +{
> + /*
> + * IHI0070G.b, sections 6.3.21 and 6.3.30: ADDR resets to UNKNOWN.
> + * ADDR == 0 disables MSIs while allowing wired IRQs. The corresponding
> + * IRQ_CTRL and IRQ_CTRLACK enable bits must be clear before writing.
> + */
> + writeq_relaxed(0, smmu->base + ARM_SMMU_GERROR_IRQ_CFG0);
> + writeq_relaxed(0, smmu->base + ARM_SMMU_EVTQ_IRQ_CFG0);
> +
> + if (smmu->features & ARM_SMMU_FEAT_PRI)
> + writeq_relaxed(0, smmu->base + ARM_SMMU_PRIQ_IRQ_CFG0);
> +}
> +
> #ifdef CONFIG_MSI
> static void arm_smmu_free_msis(void *data)
> {
> @@ -1921,13 +1949,7 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
> int ret, nvec = ARM_SMMU_MAX_MSIS;
> struct device *dev = smmu->dev;
>
> - /* Clear the MSI address regs */
> - writeq_relaxed(0, smmu->base + ARM_SMMU_GERROR_IRQ_CFG0);
> - writeq_relaxed(0, smmu->base + ARM_SMMU_EVTQ_IRQ_CFG0);
> -
> - if (smmu->features & ARM_SMMU_FEAT_PRI)
> - writeq_relaxed(0, smmu->base + ARM_SMMU_PRIQ_IRQ_CFG0);
> - else
> + if (!(smmu->features & ARM_SMMU_FEAT_PRI))
> nvec--;
>
> if (!(smmu->features & ARM_SMMU_FEAT_MSI))
> @@ -1968,7 +1990,8 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
> static inline void arm_smmu_setup_msis(struct arm_smmu_device *smmu) { }
> #endif /* CONFIG_MSI */
>
> -static void __init arm_smmu_free_irqs(struct arm_smmu_device *smmu)
> +static void init_or_smmu_suspend
> +arm_smmu_free_irqs(struct arm_smmu_device *smmu)
> {
> int irq;
>
> @@ -2052,19 +2075,38 @@ err_free_evtq_irq:
> return ret;
> }
>
> -static int __init arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
> +static int arm_smmu_enable_irqs(struct arm_smmu_device *smmu)
> {
> - int ret, irq;
> + int ret;
> u32 irqen_flags = IRQ_CTRL_EVTQ_IRQEN | IRQ_CTRL_GERROR_IRQEN;
>
> - /* Disable IRQs first */
> - ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_IRQ_CTRL,
> - ARM_SMMU_IRQ_CTRLACK);
> - if (ret) {
> - dev_err(smmu->dev, "failed to disable irqs\n");
> + if ( smmu->features & ARM_SMMU_FEAT_PRI )
> + irqen_flags |= IRQ_CTRL_PRIQ_IRQEN;
> +
> + /* Enable interrupt generation on the SMMU */
> + ret = arm_smmu_write_reg_sync(smmu, irqen_flags,
> + ARM_SMMU_IRQ_CTRL, ARM_SMMU_IRQ_CTRLACK);
> + if ( ret )
> + {
> + dev_warn(smmu->dev, "failed to enable irqs\n");
> return ret;
> }
>
> + return 0;
> +}
> +
> +static int arm_smmu_disable_irqs(struct arm_smmu_device *smmu)
> +{
> + return arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_IRQ_CTRL,
> + ARM_SMMU_IRQ_CTRLACK);
> +}
> +
> +/* Probe-time only; reset has configured the queues and disabled IRQs. */
> +static int init_or_smmu_suspend
> +arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
> +{
> + int ret, irq;
> +
> irq = smmu->combined_irq;
> if (irq) {
> /*
> @@ -2085,22 +2127,7 @@ static int __init arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
> }
> }
>
> - if (smmu->features & ARM_SMMU_FEAT_PRI)
> - irqen_flags |= IRQ_CTRL_PRIQ_IRQEN;
> -
> - /* Enable interrupt generation on the SMMU */
> - ret = arm_smmu_write_reg_sync(smmu, irqen_flags,
> - ARM_SMMU_IRQ_CTRL, ARM_SMMU_IRQ_CTRLACK);
> - if (ret) {
> - dev_warn(smmu->dev, "failed to enable irqs\n");
> - goto err_free_irqs;
> - }
> -
> return 0;
> -
> -err_free_irqs:
> - arm_smmu_free_irqs(smmu);
> - return ret;
> }
>
> static int arm_smmu_device_disable(struct arm_smmu_device *smmu)
> @@ -2114,18 +2141,31 @@ static int arm_smmu_device_disable(struct arm_smmu_device *smmu)
> return ret;
> }
>
> -static int __init arm_smmu_device_reset(struct arm_smmu_device *smmu)
> +static int init_or_smmu_suspend
> +arm_smmu_device_reset(struct arm_smmu_device *smmu, bool resume)
> {
> int ret;
> u32 reg, enables;
> struct arm_smmu_cmdq_ent cmd;
>
> + ret = arm_smmu_disable_irqs(smmu);
> + if (ret) {
> + dev_err(smmu->dev, "failed to disable irqs\n");
> + return ret;
> + }
> +
> + /* A pending GERROR IRQ must not access CMDQ while it is reset. */
> + write_atomic(&smmu->gerror_blocked, true);
> + arm_smmu_clear_msi_cfg(smmu);
> +
> /* Clear CR0 and sync (disables SMMU and queue processing) */
> reg = readl_relaxed(smmu->base + ARM_SMMU_CR0);
> if (reg & CR0_SMMUEN) {
> dev_warn(smmu->dev, "SMMU currently enabled! Resetting...\n");
> WARN_ON(!disable_bypass);
> - arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0);
> + ret = arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0);
> + if (ret)
> + return ret;
> }
>
> ret = arm_smmu_device_disable(smmu);
> @@ -2164,10 +2204,15 @@ static int __init arm_smmu_device_reset(struct arm_smmu_device *smmu)
> return ret;
> }
>
> + /* GERROR handling can use CMDQ again once its registers are restored. */
> + write_atomic(&smmu->gerror_blocked, false);
> +
> /* Invalidate any cached configuration */
> cmd.opcode = CMDQ_OP_CFGI_ALL;
> arm_smmu_cmdq_issue_cmd(smmu, &cmd);
> - arm_smmu_cmdq_issue_sync(smmu);
> + ret = arm_smmu_cmdq_issue_sync(smmu);
> + if (ret)
> + return ret;
>
> /* Invalidate any stale TLB entries */
> if (smmu->features & ARM_SMMU_FEAT_HYP) {
> @@ -2177,7 +2222,9 @@ static int __init arm_smmu_device_reset(struct arm_smmu_device *smmu)
>
> cmd.opcode = CMDQ_OP_TLBI_NSNH_ALL;
> arm_smmu_cmdq_issue_cmd(smmu, &cmd);
> - arm_smmu_cmdq_issue_sync(smmu);
> + ret = arm_smmu_cmdq_issue_sync(smmu);
> + if (ret)
> + return ret;
>
> /* Event queue */
> writeq_relaxed(smmu->evtq.q.q_base, smmu->base + ARM_SMMU_EVTQ_BASE);
> @@ -2220,17 +2267,18 @@ static int __init arm_smmu_device_reset(struct arm_smmu_device *smmu)
> }
> }
>
> - ret = arm_smmu_setup_irqs(smmu);
> - if (ret) {
> - dev_err(smmu->dev, "failed to setup irqs\n");
> - return ret;
> + /* Register handlers only after their queues and tasklets are ready. */
> + if (!resume) {
> + ret = arm_smmu_setup_irqs(smmu);
> + if (ret) {
> + dev_err(smmu->dev, "failed to setup irqs\n");
> + return ret;
> + }
> }
>
> - /* Initialize tasklets for threaded IRQs*/
> - tasklet_init(&smmu->evtq_irq_tasklet, arm_smmu_evtq_tasklet, smmu);
> - tasklet_init(&smmu->priq_irq_tasklet, arm_smmu_priq_tasklet, smmu);
> - tasklet_init(&smmu->combined_irq_tasklet, arm_smmu_combined_irq_tasklet,
> - smmu);
> + ret = arm_smmu_enable_irqs(smmu);
> + if (ret)
> + goto err_free_irqs;
>
> /* Enable the SMMU interface, or ensure bypass */
> if (disable_bypass) {
> @@ -2247,10 +2295,18 @@ static int __init arm_smmu_device_reset(struct arm_smmu_device *smmu)
> goto err_free_irqs;
> }
>
> + /* IHI0070G.b, section 6.3.16: re-enabling IRQs does not replay events. */
> + if (resume)
> + tasklet_schedule(&smmu->evtq_irq_tasklet);
> + if (resume && (smmu->features & ARM_SMMU_FEAT_PRI) &&
> + !queue_empty(&smmu->priq.q.llq))
> + tasklet_schedule(&smmu->priq_irq_tasklet);
> +
> return 0;
>
> err_free_irqs:
> - arm_smmu_free_irqs(smmu);
> + if (!resume)
> + arm_smmu_free_irqs(smmu);
> return ret;
> }
>
> @@ -2615,10 +2671,21 @@ static int __init arm_smmu_device_probe(struct platform_device *pdev)
> if (ret)
> goto out_free;
>
> + /* Initialize tasklets for threaded IRQs*/
> + tasklet_init(&smmu->evtq_irq_tasklet, arm_smmu_evtq_tasklet, smmu);
> + tasklet_init(&smmu->priq_irq_tasklet, arm_smmu_priq_tasklet, smmu);
> + tasklet_init(&smmu->combined_irq_tasklet, arm_smmu_combined_irq_tasklet,
> + smmu);
> +
> /* Reset the device */
> - ret = arm_smmu_device_reset(smmu);
> - if (ret)
> + ret = arm_smmu_device_reset(smmu, false);
> + if (ret) {
> + /* Reset may have enabled queues before failing. */
> + if (arm_smmu_device_disable(smmu))
> + panic("SMMUv3: %s: Failed to disable during probe cleanup\n",
> + dev_name(smmu->dev));
> goto out_free;
> + }
>
> /*
> * Keep a list of all probed devices. This will be used to query
> @@ -2632,7 +2699,6 @@ static int __init arm_smmu_device_probe(struct platform_device *pdev)
>
> return 0;
>
> -
> out_free:
> arm_smmu_free_structures(smmu);
> if (smmu->page1)
> @@ -2912,6 +2978,142 @@ static void arm_smmu_iommu_xen_domain_teardown(struct domain *d)
> xfree(xen_domain);
> }
>
> +#ifdef CONFIG_SYSTEM_SUSPEND
> +
> +static void arm_smmu_save_queue_producers(struct arm_smmu_device *smmu)
> +{
> + /*
> + * IHI0070G.b, sections 6.3.9.4 and 6.3.9.5: EVTQ/PRIQ disable
> + * acknowledgements make committed entries visible. The caller must
> + * wait for these acknowledgements before reading the producer indices.
> + */
> + if (queue_sync_prod_in(&smmu->evtq.q) == -EOVERFLOW)
> + dev_warn(smmu->dev, "EVTQ overflow detected during suspend\n");
> + if ((smmu->features & ARM_SMMU_FEAT_PRI) &&
> + queue_sync_prod_in(&smmu->priq.q) == -EOVERFLOW)
> + dev_warn(smmu->dev, "PRIQ overflow detected during suspend\n");
> +}
> +
> +static void arm_smmu_reset_for_suspend_rollback(struct arm_smmu_device *smmu)
> +{
> + int ret;
> + u32 reg;
> +
> + /*
> + * The queues have been requested to stop, but a CR0ACK timeout may
> + * have skipped saving their producer indices. Wait for the queue
> + * disable acknowledgements before reset overwrites those indices.
> + */
> + ret = readl_relaxed_poll_timeout(smmu->base + ARM_SMMU_CR0ACK, reg,
> + !(reg & (CR0_EVTQEN | CR0_PRIQEN)),
> + 1, ARM_SMMU_POLL_TIMEOUT_US);
> + if (ret)
> + panic("SMMUv3: %s: Queue stop timed out during rollback: %d\n",
> + dev_name(smmu->dev), ret);
> +
> + arm_smmu_save_queue_producers(smmu);
> + ret = arm_smmu_device_reset(smmu, true);
> +
> + /* The host suspend error path allows domains to run again. */
> + if ( ret )
> + panic("SMMUv3: %s: Failed to reset during suspend rollback: %d\n",
> + dev_name(smmu->dev), ret);
> +}
> +
> +static int arm_smmu_suspend(void)
> +{
> + struct arm_smmu_device *smmu;
> + int ret = 0;
> +
> + list_for_each_entry(smmu, &arm_smmu_devices, devices)
> + {
> + /* Abort all transactions before disable to avoid spurious bypass */
> + ret = arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0);
> + if ( ret )
> + goto rollback_previous;
> +
> + /* Disable the SMMU via CR0.EN and all queues except CMDQ */
> + ret = arm_smmu_write_reg_sync(smmu, CR0_CMDQEN, ARM_SMMU_CR0,
> + ARM_SMMU_CR0ACK);
> + if ( ret )
> + {
> + dev_err(smmu->dev, "Timed-out while disabling smmu\n");
> + goto fail;
> + }
> +
> + arm_smmu_save_queue_producers(smmu);
> +
> + /*
> + * At this point the translation interface is disabled and the
> + * SMMU won't access translation/config structures, even
> + * speculatively, as per the IHI0070 spec (section 6.3.9.6).
> + * CMDQ is still enabled so that a CMD_SYNC can complete any
> + * previously issued commands.
> + */
> +
> + /* Ensure all previously issued commands have completed. */
> + ret = arm_smmu_cmdq_issue_sync(smmu);
> + if ( ret )
> + {
> + dev_err(smmu->dev, "Timed-out waiting for pending commands\n");
> + goto fail;
> + }
> +
> + /* Stop IRQ generation before gating the handler and disabling CMDQ. */
> + ret = arm_smmu_disable_irqs(smmu);
> + if (ret) {
> + dev_err(smmu->dev, "Timed-out while disabling SMMU irqs\n");
> + goto fail;
> + }
> + write_atomic(&smmu->gerror_blocked, true);
> +
> + /* Disable everything */
> + ret = arm_smmu_device_disable(smmu);
> + if ( ret )
> + goto fail;
> +
> + /* Other CPUs are offline and the IRQ handler is gated above. */
> + arm_smmu_handle_gerror(smmu);
> +
> + dev_dbg(smmu->dev, "Suspended smmu\n");
> + }
> +
> + return 0;
> +
> + fail:
> + /* Reset the device that failed as well as any already-suspended ones. */
> + arm_smmu_reset_for_suspend_rollback(smmu);
> +
> + rollback_previous:
> + /* An initial GBPA failure leaves this SMMU enabled: do not reset it. */
> + list_for_each_entry_continue_reverse(smmu, &arm_smmu_devices, devices)
> + arm_smmu_reset_for_suspend_rollback(smmu);
> +
> + return ret;
> +}
> +
> +static void arm_smmu_resume(void)
> +{
> + int ret;
> + struct arm_smmu_device *smmu;
> +
> + list_for_each_entry(smmu, &arm_smmu_devices, devices)
> + {
> + dev_dbg(smmu->dev, "Resuming device\n");
> +
> + /*
> + * The reset will re-initialize all the base addresses, queues,
> + * prod and cons maintained within struct arm_smmu_device as well as
> + * re-enable the interrupts.
> + */
> + ret = arm_smmu_device_reset(smmu, true);
> + if ( ret )
> + panic("SMMUv3: %s: Failed to reset during resume: %d\n",
> + dev_name(smmu->dev), ret);
> + }
> +}
> +#endif
> +
> static const struct iommu_ops arm_smmu_iommu_ops = {
> .page_sizes = PAGE_SIZE_4K,
> .init = arm_smmu_iommu_xen_domain_init,
> @@ -2925,6 +3127,10 @@ static const struct iommu_ops arm_smmu_iommu_ops = {
> .dt_xlate = arm_smmu_dt_xlate,
> .add_device = arm_smmu_add_device,
> .remove_device = arm_smmu_remove_device,
> +#ifdef CONFIG_SYSTEM_SUSPEND
> + .suspend = arm_smmu_suspend,
> + .resume = arm_smmu_resume,
> +#endif
> };
>
> static __init int arm_smmu_dt_init(struct dt_device_node *dev,
> diff --git a/xen/drivers/passthrough/arm/smmu-v3.h b/xen/drivers/passthrough/arm/smmu-v3.h
> index ab07366294..93986886f2 100644
> --- a/xen/drivers/passthrough/arm/smmu-v3.h
> +++ b/xen/drivers/passthrough/arm/smmu-v3.h
> @@ -613,6 +613,7 @@ struct arm_smmu_device {
> int combined_irq;
> u32 sync_nr;
> u8 prev_cmd_opcode;
> + bool gerror_blocked;
>
> unsigned long ias; /* IPA */
> unsigned long oas; /* PA */
> --
> 2.53.0
^ permalink raw reply [flat|nested] 20+ messages in thread
* [PATCH v14 11/15] xen/arm64: Keep the early UART message in the identity mapping
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (9 preceding siblings ...)
2026-11-17 1:05 ` [PATCH v14 10/15] xen/arm: smmu-v3: add suspend/resume handlers Mykola Kvach
@ 2026-11-17 1:05 ` Mykola Kvach
2026-11-17 16:59 ` Bertrand Marquis
2026-11-17 1:05 ` [PATCH v14 12/15] xen/arm64: Save/restore CPU context across SYSTEM_SUSPEND Mykola Kvach
` (3 subsequent siblings)
14 siblings, 1 reply; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:05 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk
init_uart() uses PRINT(), which places the UART message in .rodata.str.
This works during boot, before cache coloring relocates Xen.
The upcoming SYSTEM_SUSPEND resume path will also call init_uart() with
the MMU disabled. With cache coloring, Xen is no longer physically
contiguous, so the PC-relative address used by PRINT() may not point to
the string's physical location.
Use PRINT_ID() to keep the message in .rodata.idmap, alongside the code
that needs it before enabling the MMU.
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
---
Changes in v14:
- New patch.
---
xen/arch/arm/arm64/head.S | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/xen/arch/arm/arm64/head.S b/xen/arch/arm/arm64/head.S
index 7d1e205353..f523427d48 100644
--- a/xen/arch/arm/arm64/head.S
+++ b/xen/arch/arm/arm64/head.S
@@ -447,7 +447,7 @@ FUNC_LOCAL(init_uart)
#ifdef CONFIG_EARLY_UART_INIT
early_uart_init x23, 0
#endif
- PRINT("- UART enabled -\r\n")
+ PRINT_ID("- UART enabled -\r\n")
ret
END(init_uart)
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* Re: [PATCH v14 11/15] xen/arm64: Keep the early UART message in the identity mapping
2026-11-17 1:05 ` [PATCH v14 11/15] xen/arm64: Keep the early UART message in the identity mapping Mykola Kvach
@ 2026-11-17 16:59 ` Bertrand Marquis
0 siblings, 0 replies; 20+ messages in thread
From: Bertrand Marquis @ 2026-11-17 16:59 UTC (permalink / raw)
To: Mykola Kvach
Cc: xen-devel@lists.xenproject.org, Stefano Stabellini, Julien Grall,
Michal Orzel, Volodymyr Babchuk
Hi Mykola,
> On 17 Nov 2026, at 02:05, Mykola Kvach <mykola_kvach@epam.com> wrote:
>
> init_uart() uses PRINT(), which places the UART message in .rodata.str.
> This works during boot, before cache coloring relocates Xen.
>
> The upcoming SYSTEM_SUSPEND resume path will also call init_uart() with
> the MMU disabled. With cache coloring, Xen is no longer physically
> contiguous, so the PC-relative address used by PRINT() may not point to
> the string's physical location.
>
> Use PRINT_ID() to keep the message in .rodata.idmap, alongside the code
> that needs it before enabling the MMU.
>
> Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
Cheers
Bertrand
> ---
> Changes in v14:
> - New patch.
> ---
> xen/arch/arm/arm64/head.S | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/xen/arch/arm/arm64/head.S b/xen/arch/arm/arm64/head.S
> index 7d1e205353..f523427d48 100644
> --- a/xen/arch/arm/arm64/head.S
> +++ b/xen/arch/arm/arm64/head.S
> @@ -447,7 +447,7 @@ FUNC_LOCAL(init_uart)
> #ifdef CONFIG_EARLY_UART_INIT
> early_uart_init x23, 0
> #endif
> - PRINT("- UART enabled -\r\n")
> + PRINT_ID("- UART enabled -\r\n")
> ret
> END(init_uart)
>
> --
> 2.53.0
^ permalink raw reply [flat|nested] 20+ messages in thread
* [PATCH v14 12/15] xen/arm64: Save/restore CPU context across SYSTEM_SUSPEND
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (10 preceding siblings ...)
2026-11-17 1:05 ` [PATCH v14 11/15] xen/arm64: Keep the early UART message in the identity mapping Mykola Kvach
@ 2026-11-17 1:05 ` Mykola Kvach
2026-11-17 1:05 ` [PATCH v14 13/15] xen/arm: Implement PSCI SYSTEM_SUSPEND call (host interface) Mykola Kvach
` (2 subsequent siblings)
14 siblings, 0 replies; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:05 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk, Oleksandr Tyshchenko,
Luca Fancellu
From: Mirela Simonovic <mirela.simonovic@aggios.com>
On wakeup from PSCI SYSTEM_SUSPEND, Xen re-enters EL2 with the MMU and
data cache disabled. The resume path must first switch back to Xen's
runtime page tables before it can access the saved CPU context using
virtual addresses.
Add an arm64 hyp_resume trampoline that reuses enable_secondary_cpu_mm()
to enable the data cache and MMU, switch to init_ttbr, and resume in the
runtime virtual mapping. The trampoline then restores the saved CPU
general-purpose and system-control register context.
prepare_resume_ctx() must be invoked just before the PSCI system suspend
call is issued to the platform firmware. It saves the current CPU context
and returns a non-zero value so that the caller enters the physical
SYSTEM_SUSPEND call.
On resume, hyp_resume restores the saved context, including the saved link
register. Control therefore returns to the place where prepare_resume_ctx()
was called. To avoid re-entering the suspend path, the restored path sees
prepare_resume_ctx() return zero.
The assembly save/restore code uses offsets generated by asm-offsets.c
from struct resume_cpu_context, keeping the assembly memory accesses in
sync with the C structure layout.
Support for ARM32 is not implemented. Instead, compilation fails with a
build-time error if suspend is enabled for ARM32.
Signed-off-by: Mirela Simonovic <mirela.simonovic@aggios.com>
Signed-off-by: Saeed Nowshadi <saeed.nowshadi@xilinx.com>
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Reviewed-by: Luca Fancellu <luca.fancellu@arm.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
---
Changes in v10:
- Save and restore CNTHCTL_EL2 across SYSTEM_SUSPEND
Changes in v9:
- Drop the misleading prepare_resume_ctx() pointer argument and make both
save/restore paths use the global resume_cpu_context.
- Squash the arm64 resume trampoline into the context save/restore patch.
- Document in code that hyp_resume relies on PSCI initial-state rules.
- Use generic platform firmware wording instead of ATF-specific wording.
- Rename the saved context type/storage to resume_cpu_context and rely on
implicit zero-initialization for the file-scope object.
- Use asm-offsets.c-generated RESUME_CTX_* offsets to keep the assembly
save/restore code in sync with struct resume_cpu_context.
Changes in v8:
- Fix alignments in code.
Changes in v7:
- No functional changes, just moved commit.
---
xen/arch/arm/Makefile | 1 +
xen/arch/arm/arm64/asm-offsets.c | 21 +++++
xen/arch/arm/arm64/head.S | 122 +++++++++++++++++++++++++++++
xen/arch/arm/include/asm/suspend.h | 27 +++++++
xen/arch/arm/suspend.c | 14 ++++
5 files changed, 185 insertions(+)
create mode 100644 xen/arch/arm/suspend.c
diff --git a/xen/arch/arm/Makefile b/xen/arch/arm/Makefile
index cdcec8cd03..09640090b4 100644
--- a/xen/arch/arm/Makefile
+++ b/xen/arch/arm/Makefile
@@ -52,6 +52,7 @@ obj-y += setup.o
obj-y += shutdown.o
obj-y += smp.o
obj-y += smpboot.o
+obj-$(CONFIG_SYSTEM_SUSPEND) += suspend.o
obj-$(CONFIG_SYSCTL) += sysctl.o
obj-y += time.o
obj-y += traps.o
diff --git a/xen/arch/arm/arm64/asm-offsets.c b/xen/arch/arm/arm64/asm-offsets.c
index 38a3894a3b..5d60406e9c 100644
--- a/xen/arch/arm/arm64/asm-offsets.c
+++ b/xen/arch/arm/arm64/asm-offsets.c
@@ -13,6 +13,7 @@
#include <asm/mm.h>
#include <asm/setup.h>
#include <asm/smccc.h>
+#include <asm/suspend.h>
#define DEFINE(_sym, _val) \
asm volatile ( "\n.ascii\"==>#define " #_sym " %0 /* " #_val " */<==\""\
@@ -57,6 +58,26 @@ void __dummy__(void)
OFFSET(INITINFO_stack, struct init_info, stack);
BLANK();
+#ifdef CONFIG_SYSTEM_SUSPEND
+ OFFSET(RESUME_CTX_X19, struct resume_cpu_context, callee_regs[0]);
+ OFFSET(RESUME_CTX_X21, struct resume_cpu_context, callee_regs[2]);
+ OFFSET(RESUME_CTX_X23, struct resume_cpu_context, callee_regs[4]);
+ OFFSET(RESUME_CTX_X25, struct resume_cpu_context, callee_regs[6]);
+ OFFSET(RESUME_CTX_X27, struct resume_cpu_context, callee_regs[8]);
+ OFFSET(RESUME_CTX_X29, struct resume_cpu_context, callee_regs[10]);
+ OFFSET(RESUME_CTX_SP, struct resume_cpu_context, sp);
+ OFFSET(RESUME_CTX_VBAR_EL2, struct resume_cpu_context, vbar_el2);
+ OFFSET(RESUME_CTX_VTCR_EL2, struct resume_cpu_context, vtcr_el2);
+ OFFSET(RESUME_CTX_VTTBR_EL2, struct resume_cpu_context, vttbr_el2);
+ OFFSET(RESUME_CTX_TPIDR_EL2, struct resume_cpu_context, tpidr_el2);
+ OFFSET(RESUME_CTX_MDCR_EL2, struct resume_cpu_context, mdcr_el2);
+ OFFSET(RESUME_CTX_HSTR_EL2, struct resume_cpu_context, hstr_el2);
+ OFFSET(RESUME_CTX_CPTR_EL2, struct resume_cpu_context, cptr_el2);
+ OFFSET(RESUME_CTX_HCR_EL2, struct resume_cpu_context, hcr_el2);
+ OFFSET(RESUME_CTX_CNTHCTL_EL2, struct resume_cpu_context, cnthctl_el2);
+ BLANK();
+#endif
+
OFFSET(SMCCC_RES_a0, struct arm_smccc_res, a0);
OFFSET(SMCCC_RES_a2, struct arm_smccc_res, a2);
OFFSET(ARM_SMCCC_1_2_REGS_X0_OFFS, struct arm_smccc_1_2_regs, a0);
diff --git a/xen/arch/arm/arm64/head.S b/xen/arch/arm/arm64/head.S
index f523427d48..0c78c3750e 100644
--- a/xen/arch/arm/arm64/head.S
+++ b/xen/arch/arm/arm64/head.S
@@ -563,6 +563,128 @@ END(efi_xen_start)
#endif /* CONFIG_ARM_EFI */
+#ifdef CONFIG_SYSTEM_SUSPEND
+/*
+ * int prepare_resume_ctx(void)
+ *
+ * CPU context saved here will be restored on resume in hyp_resume function.
+ * prepare_resume_ctx shall return a non-zero value. Upon restoring context
+ * hyp_resume shall return value zero instead. From C code that invokes
+ * prepare_resume_ctx, the return value is interpreted to determine whether
+ * the context is saved (prepare_resume_ctx) or restored (hyp_resume).
+ */
+FUNC(prepare_resume_ctx)
+ ldr x0, =resume_cpu_context
+
+ /* Store callee-saved registers */
+ stp x19, x20, [x0, #RESUME_CTX_X19]
+ stp x21, x22, [x0, #RESUME_CTX_X21]
+ stp x23, x24, [x0, #RESUME_CTX_X23]
+ stp x25, x26, [x0, #RESUME_CTX_X25]
+ stp x27, x28, [x0, #RESUME_CTX_X27]
+ stp x29, lr, [x0, #RESUME_CTX_X29]
+
+ /* Store stack-pointer */
+ mov x2, sp
+ str x2, [x0, #RESUME_CTX_SP]
+
+ /* Store system control registers */
+ mrs x2, VBAR_EL2
+ str x2, [x0, #RESUME_CTX_VBAR_EL2]
+ mrs x2, VTCR_EL2
+ str x2, [x0, #RESUME_CTX_VTCR_EL2]
+ mrs x2, VTTBR_EL2
+ str x2, [x0, #RESUME_CTX_VTTBR_EL2]
+ mrs x2, TPIDR_EL2
+ str x2, [x0, #RESUME_CTX_TPIDR_EL2]
+ mrs x2, MDCR_EL2
+ str x2, [x0, #RESUME_CTX_MDCR_EL2]
+ mrs x2, HSTR_EL2
+ str x2, [x0, #RESUME_CTX_HSTR_EL2]
+ mrs x2, CPTR_EL2
+ str x2, [x0, #RESUME_CTX_CPTR_EL2]
+ mrs x2, HCR_EL2
+ str x2, [x0, #RESUME_CTX_HCR_EL2]
+ mrs x2, CNTHCTL_EL2
+ str x2, [x0, #RESUME_CTX_CNTHCTL_EL2]
+
+ /* prepare_resume_ctx must return a non-zero value */
+ mov x0, #1
+ ret
+END(prepare_resume_ctx)
+
+FUNC(hyp_resume)
+ /*
+ * PSCI states that SYSTEM_SUSPEND follows the CPU_SUSPEND initial
+ * state rules, so PSCI-compliant firmware must enter the return
+ * exception level with DAIF masked.
+ */
+
+ /* Initialize the UART if earlyprintk has been enabled. */
+#ifdef CONFIG_EARLY_PRINTK
+ bl init_uart
+#endif
+ PRINT_ID("- Xen resuming -\r\n")
+
+ bl check_cpu_mode
+ bl cpu_init
+
+ ldr x0, =start
+ adr x20, start /* x20 := paddr (start) */
+ sub x20, x20, x0 /* x20 := phys-offset */
+ ldr lr, =mmu_resumed
+ b enable_secondary_cpu_mm
+
+mmu_resumed:
+ /* Now we can access the saved context, so restore it here. */
+ ldr x0, =resume_cpu_context
+
+ /* Restore callee-saved registers */
+ ldp x19, x20, [x0, #RESUME_CTX_X19]
+ ldp x21, x22, [x0, #RESUME_CTX_X21]
+ ldp x23, x24, [x0, #RESUME_CTX_X23]
+ ldp x25, x26, [x0, #RESUME_CTX_X25]
+ ldp x27, x28, [x0, #RESUME_CTX_X27]
+ ldp x29, lr, [x0, #RESUME_CTX_X29]
+
+ /* Restore stack pointer */
+ ldr x2, [x0, #RESUME_CTX_SP]
+ mov sp, x2
+
+ /* Restore system control registers */
+ ldr x2, [x0, #RESUME_CTX_VBAR_EL2]
+ msr VBAR_EL2, x2
+ ldr x2, [x0, #RESUME_CTX_VTCR_EL2]
+ msr VTCR_EL2, x2
+ ldr x2, [x0, #RESUME_CTX_VTTBR_EL2]
+ msr VTTBR_EL2, x2
+ ldr x2, [x0, #RESUME_CTX_TPIDR_EL2]
+ msr TPIDR_EL2, x2
+ ldr x2, [x0, #RESUME_CTX_MDCR_EL2]
+ msr MDCR_EL2, x2
+ ldr x2, [x0, #RESUME_CTX_HSTR_EL2]
+ msr HSTR_EL2, x2
+ ldr x2, [x0, #RESUME_CTX_CPTR_EL2]
+ msr CPTR_EL2, x2
+ ldr x2, [x0, #RESUME_CTX_HCR_EL2]
+ msr HCR_EL2, x2
+ ldr x2, [x0, #RESUME_CTX_CNTHCTL_EL2]
+ msr CNTHCTL_EL2, x2
+ isb
+
+ /*
+ * Since context is restored return from this function will appear
+ * as return from prepare_resume_ctx. To distinguish a return from
+ * prepare_resume_ctx which is called upon finalizing the suspend,
+ * as opposed to return from this function which executes on resume,
+ * we need to return zero value here.
+ */
+ mov x0, #0
+ ret
+END(hyp_resume)
+
+#endif /* CONFIG_SYSTEM_SUSPEND */
+
/*
* Local variables:
* mode: ASM
diff --git a/xen/arch/arm/include/asm/suspend.h b/xen/arch/arm/include/asm/suspend.h
index 31a98a1f1b..c848fc6340 100644
--- a/xen/arch/arm/include/asm/suspend.h
+++ b/xen/arch/arm/include/asm/suspend.h
@@ -3,6 +3,8 @@
#ifndef ARM_SUSPEND_H
#define ARM_SUSPEND_H
+#include <xen/types.h>
+
struct domain;
struct vcpu;
struct vcpu_guest_context;
@@ -14,6 +16,31 @@ struct resume_info {
void arch_domain_resume(struct domain *d);
+#ifdef CONFIG_SYSTEM_SUSPEND
+#ifdef CONFIG_ARM_64
+struct resume_cpu_context {
+ register_t callee_regs[12];
+ register_t sp;
+ register_t vbar_el2;
+ register_t vtcr_el2;
+ register_t vttbr_el2;
+ register_t tpidr_el2;
+ register_t mdcr_el2;
+ register_t hstr_el2;
+ register_t cptr_el2;
+ register_t hcr_el2;
+ register_t cnthctl_el2;
+} __aligned(16);
+#else
+#error "Define resume_cpu_context structure for arm32"
+#endif
+
+extern struct resume_cpu_context resume_cpu_context;
+
+int prepare_resume_ctx(void);
+void hyp_resume(void);
+#endif /* CONFIG_SYSTEM_SUSPEND */
+
#endif /* ARM_SUSPEND_H */
/*
diff --git a/xen/arch/arm/suspend.c b/xen/arch/arm/suspend.c
new file mode 100644
index 0000000000..6ea4a0f9cc
--- /dev/null
+++ b/xen/arch/arm/suspend.c
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <asm/suspend.h>
+
+struct resume_cpu_context resume_cpu_context;
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v14 13/15] xen/arm: Implement PSCI SYSTEM_SUSPEND call (host interface)
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (11 preceding siblings ...)
2026-11-17 1:05 ` [PATCH v14 12/15] xen/arm64: Save/restore CPU context across SYSTEM_SUSPEND Mykola Kvach
@ 2026-11-17 1:05 ` Mykola Kvach
2026-11-17 1:05 ` [PATCH v14 14/15] xen/arm: Add vPSCI SYSTEM_SUSPEND policy Mykola Kvach
2026-11-17 1:05 ` [PATCH v14 15/15] xen/arm: Add host system suspend backend Mykola Kvach
14 siblings, 0 replies; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:05 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk, Luca Fancellu
From: Mirela Simonovic <mirela.simonovic@aggios.com>
Invoke PSCI SYSTEM_SUSPEND to finalize Xen's suspend sequence on ARM64
platforms. Pass the Xen resume entry point (hyp_resume) to EL3 together
with a zero context ID, matching Linux.
This patch wires up only the host-side PSCI SYSTEM_SUSPEND invocation.
The resume trampoline and context restore are provided by earlier patches
in the series.
Only enable this path when CONFIG_SYSTEM_SUSPEND is set and PSCI
advertises SYSTEM_SUSPEND via PSCI_FEATURES.
Signed-off-by: Mirela Simonovic <mirela.simonovic@aggios.com>
Signed-off-by: Saeed Nowshadi <saeed.nowshadi@xilinx.com>
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Luca Fancellu <luca.fancellu@arm.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
---
Changes in v13:
- Use the result returned by arm_smccc_smc() and drop the result pointer.
Changes in v9:
- cache SYSTEM_SUSPEND support using PSCI_FEATURES and gate the host call
on the cached capability
- keep the cached SYSTEM_SUSPEND capability read-only after init
- log whether firmware reports SYSTEM_SUSPEND support
- pass an explicit zero context ID in the SYSTEM_SUSPEND call
- drop the stale note claiming hyp_resume is still a stub
---
xen/arch/arm/include/asm/psci.h | 1 +
xen/arch/arm/psci.c | 32 +++++++++++++++++++++++++++++++-
2 files changed, 32 insertions(+), 1 deletion(-)
diff --git a/xen/arch/arm/include/asm/psci.h b/xen/arch/arm/include/asm/psci.h
index 48a93e6b79..bb3c73496e 100644
--- a/xen/arch/arm/include/asm/psci.h
+++ b/xen/arch/arm/include/asm/psci.h
@@ -23,6 +23,7 @@ int call_psci_cpu_on(int cpu);
void call_psci_cpu_off(void);
void call_psci_system_off(void);
void call_psci_system_reset(void);
+int call_psci_system_suspend(void);
/* Range of allocated PSCI function numbers */
#define PSCI_FNUM_MIN_VALUE _AC(0,U)
diff --git a/xen/arch/arm/psci.c b/xen/arch/arm/psci.c
index 79947b124b..294e53a29f 100644
--- a/xen/arch/arm/psci.c
+++ b/xen/arch/arm/psci.c
@@ -17,23 +17,27 @@
#include <asm/cpufeature.h>
#include <asm/psci.h>
#include <asm/acpi.h>
+#include <asm/suspend.h>
/*
* While a 64-bit OS can make calls with SMC32 calling conventions, for
* some calls it is necessary to use SMC64 to pass or return 64-bit values.
- * For such calls PSCI_0_2_FN_NATIVE(x) will choose the appropriate
+ * For such calls PSCI_*_FN_NATIVE(x) will choose the appropriate
* (native-width) function ID.
*/
#ifdef CONFIG_ARM_64
#define PSCI_0_2_FN_NATIVE(name) PSCI_0_2_FN64_##name
+#define PSCI_1_0_FN_NATIVE(name) PSCI_1_0_FN64_##name
#else
#define PSCI_0_2_FN_NATIVE(name) PSCI_0_2_FN32_##name
+#define PSCI_1_0_FN_NATIVE(name) PSCI_1_0_FN32_##name
#endif
uint32_t psci_ver;
uint32_t smccc_ver;
static uint32_t psci_cpu_on_nr;
+static bool __ro_after_init has_psci_system_suspend;
#define PSCI_RET(res) ((int32_t)(res).a0)
@@ -60,6 +64,26 @@ void call_psci_cpu_off(void)
}
}
+int call_psci_system_suspend(void)
+{
+#ifdef CONFIG_SYSTEM_SUSPEND
+ struct arm_smccc_res res;
+
+ if ( !has_psci_system_suspend )
+ return PSCI_NOT_SUPPORTED;
+
+ /* Context ID is unused for the Xen resume path. */
+ res = arm_smccc_smc(PSCI_1_0_FN_NATIVE(SYSTEM_SUSPEND),
+ __pa(hyp_resume), 0);
+
+ return PSCI_RET(res);
+#else
+ dprintk(XENLOG_WARNING,
+ "SYSTEM_SUSPEND not supported (CONFIG_SYSTEM_SUSPEND disabled)\n");
+ return PSCI_NOT_SUPPORTED;
+#endif
+}
+
void call_psci_system_off(void)
{
if ( psci_ver > PSCI_VERSION(0, 1) )
@@ -223,9 +247,15 @@ int __init psci_init(void)
psci_init_smccc();
+ has_psci_system_suspend =
+ psci_features(PSCI_1_0_FN_NATIVE(SYSTEM_SUSPEND)) == 0;
+
printk(XENLOG_INFO "Using PSCI v%u.%u\n",
PSCI_VERSION_MAJOR(psci_ver), PSCI_VERSION_MINOR(psci_ver));
+ printk(XENLOG_DEBUG "PSCI SYSTEM_SUSPEND is %ssupported by firmware\n",
+ has_psci_system_suspend ? "" : "not ");
+
return 0;
}
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v14 14/15] xen/arm: Add vPSCI SYSTEM_SUSPEND policy
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (12 preceding siblings ...)
2026-11-17 1:05 ` [PATCH v14 13/15] xen/arm: Implement PSCI SYSTEM_SUSPEND call (host interface) Mykola Kvach
@ 2026-11-17 1:05 ` Mykola Kvach
2026-11-17 1:05 ` [PATCH v14 15/15] xen/arm: Add host system suspend backend Mykola Kvach
14 siblings, 0 replies; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:05 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk, Andrew Cooper, Anthony PERARD,
Jan Beulich, Roger Pau Monné, Mykyta Poturai, Rahul Singh
Introduce CONFIG_HAS_HWDOM_SYSTEM_SUSPEND as an architecture-selected
capability for platforms where the hardware domain can be parked with
SHUTDOWN_suspend without calling hwdom_shutdown().
Expose PSCI SYSTEM_SUSPEND as a vPSCI operation for all domains. For
non-control domains, including the hardware domain when it is not acting
as a control domain, the call is handled as a guest/domain suspend request
and parks the domain in SHUTDOWN_suspend.
A non-control domain can suspend only while a control domain exists to
resume it using XEN_DOMCTL_resumedomain. Return PSCI_DENIED otherwise,
including in a dom0less setup with no control domain.
Control domains need additional sequencing because their SYSTEM_SUSPEND
request is used to coordinate host-wide suspend. A non-last awake control
domain may be parked in SHUTDOWN_suspend without requiring the host
suspend path to be available. The last awake control domain is treated as
the point where the request becomes a host-suspend request, and it may
only proceed when all non-control domains are already in SHUTDOWN_suspend
and the host suspend path is available.
Keep the control-domain sequencing and domain-readiness checks out of
PSCI_FEATURES. They are per-attempt runtime conditions rather than stable
PSCI function availability. Advertise SYSTEM_SUSPEND as implemented by
vPSCI and report attempt-time policy failures as PSCI_DENIED.
Select HAS_HWDOM_SYSTEM_SUSPEND independently from CONFIG_SYSTEM_SUSPEND
so that SHUTDOWN_suspend from the hardware domain can be treated as a
domain suspend state rather than as a hardware-domain initiated host
shutdown. This does not by itself imply that host-wide suspend is
available.
Keep the !MPU condition to preserve the existing hardware-domain shutdown
behaviour on MPU systems. This series does not add suspend support for
Cortex-R, and suspend/resume has not been tested there. Hardware-domain
suspend also applies to ARM32 MMU systems: Xen keeps running and a
separate control domain can resume the hardware domain.
Add host_system_suspend_allowed() to combine the host PSCI SYSTEM_SUSPEND
capability with runtime blockers reported by Xen-owned subsystems. Add
runtime blockers for registered serial, IOMMU, GIC and SMMUv3 MSI IRQ
paths lacking suspend/resume support. These blockers are runtime based,
so they only apply to drivers or paths that Xen actually uses on the
platform. For SMMUv3, the blocker applies only when Xen actually uses the
MSI IRQ path, since resume does not restore the SMMU *_IRQ_CFGn MSI
registers yet.
Block host suspend when Xen uses an R-Car Gen4 PCIe controller. The
PCIe BDF-to-OSID registers are not saved and restored yet. This does
not affect normal IPMMU use or guest-only suspend.
Add a struct domain forward declaration to xen/suspend.h so the generic
header can expose arch_domain_resume() without requiring a full domain.h
include.
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com> # ARM, ARM SMMUv3
---
Changes in V14:
- Explain the !MPU condition and distinguish hardware-domain suspend
from host suspend, including availability on ARM32 MMU systems.
- Rename serial_suspend_available to suspend_possible. No functional
change.
- Wrap the SYSTEM_SUSPEND policy lock comment.
Changes in V13:
- Block host suspend when Xen uses an R-Car Gen4 PCIe controller, since
PCIe OSID state is not restored.
- Deny guest SYSTEM_SUSPEND when no control domain exists to resume it.
- Split the long suspend-state check across two lines.
Changes in V12:
- handle missing is_shut_down, change checking to call of
domain_shutdown_completed
Changes in V11:
- Mark host_system_suspend_runtime_allowed as __ro_after_init.
- Avoid printing the SMMUv3 MSI IRQ host suspend blocker more than once
when multiple SMMUv3 instances use MSIs.
- Wrap the Arm IOMMU host suspend blocker in CONFIG_SYSTEM_SUSPEND to make
its policy-only use explicit.
Changes in V10:
- Return PSCI_DENIED rather than PSCI_NOT_SUPPORTED when the last awake
control domain cannot proceed to host suspend, keeping PSCI_FEATURES
stable once SYSTEM_SUSPEND is advertised.
- Shorten SYSTEM_SUSPEND blocker messages and use %pd when logging the
control domain.
- Mark serial_suspend_available as __ro_after_init.
- Mention the struct domain forward declaration added to xen/suspend.h.
Changes in V9:
- Select HAS_HWDOM_SYSTEM_SUSPEND independently from CONFIG_SYSTEM_SUSPEND
so that hardware-domain SHUTDOWN_suspend support is not tied to
host-wide system suspend availability.
- Add runtime host suspend blockers for Xen-owned subsystems lacking
suspend/resume support.
- Keep vPSCI SYSTEM_SUSPEND advertised through PSCI_FEATURES and enforce
control-domain sequencing in the call handler.
---
xen/arch/arm/Kconfig | 1 +
xen/arch/arm/gic.c | 6 ++
xen/arch/arm/include/asm/psci.h | 3 +
xen/arch/arm/include/asm/suspend.h | 10 ++-
xen/arch/arm/pci/pci-host-rcar4.c | 4 +
xen/arch/arm/psci.c | 7 ++
xen/arch/arm/suspend.c | 40 +++++++++
xen/arch/arm/vpsci.c | 120 +++++++++++++++++++++++---
xen/common/Kconfig | 3 +
xen/common/domain.c | 7 +-
xen/drivers/char/serial.c | 12 +++
xen/drivers/passthrough/arm/iommu.c | 6 ++
xen/drivers/passthrough/arm/smmu-v3.c | 9 ++
xen/include/xen/serial.h | 1 +
xen/include/xen/suspend.h | 2 +
15 files changed, 218 insertions(+), 13 deletions(-)
diff --git a/xen/arch/arm/Kconfig b/xen/arch/arm/Kconfig
index b9c5c40678..fd5f0ddb17 100644
--- a/xen/arch/arm/Kconfig
+++ b/xen/arch/arm/Kconfig
@@ -19,6 +19,7 @@ config ARM
select HAS_ALTERNATIVE if HAS_VMAP
select HAS_DEVICE_TREE_DISCOVERY
select HAS_DOM0LESS
+ select HAS_HWDOM_SYSTEM_SUSPEND if !MPU
select HAS_GRANT_CACHE_FLUSH if GRANT_TABLE
select HAS_SHARED_INFO
select HAS_STACK_PROTECTOR
diff --git a/xen/arch/arm/gic.c b/xen/arch/arm/gic.c
index 30087b5938..3fb0a56d94 100644
--- a/xen/arch/arm/gic.c
+++ b/xen/arch/arm/gic.c
@@ -26,6 +26,7 @@
#include <asm/device.h>
#include <asm/io.h>
#include <asm/gic.h>
+#include <asm/suspend.h>
#include <asm/vgic.h>
#include <asm/acpi.h>
@@ -44,6 +45,11 @@ static void __init __maybe_unused build_assertions(void)
void register_gic_ops(const struct gic_hw_operations *ops)
{
gic_hw_ops = ops;
+
+#ifdef CONFIG_SYSTEM_SUSPEND
+ if ( !ops->suspend || !ops->resume )
+ host_system_suspend_disable("GIC driver lacks suspend support");
+#endif
}
static void clear_cpu_lr_mask(void)
diff --git a/xen/arch/arm/include/asm/psci.h b/xen/arch/arm/include/asm/psci.h
index bb3c73496e..142fa1bfe5 100644
--- a/xen/arch/arm/include/asm/psci.h
+++ b/xen/arch/arm/include/asm/psci.h
@@ -24,6 +24,9 @@ void call_psci_cpu_off(void);
void call_psci_system_off(void);
void call_psci_system_reset(void);
int call_psci_system_suspend(void);
+#ifdef CONFIG_SYSTEM_SUSPEND
+bool psci_system_suspend_allowed(void);
+#endif
/* Range of allocated PSCI function numbers */
#define PSCI_FNUM_MIN_VALUE _AC(0,U)
diff --git a/xen/arch/arm/include/asm/suspend.h b/xen/arch/arm/include/asm/suspend.h
index c848fc6340..50dc6e9fdf 100644
--- a/xen/arch/arm/include/asm/suspend.h
+++ b/xen/arch/arm/include/asm/suspend.h
@@ -39,7 +39,15 @@ extern struct resume_cpu_context resume_cpu_context;
int prepare_resume_ctx(void);
void hyp_resume(void);
-#endif /* CONFIG_SYSTEM_SUSPEND */
+bool host_system_suspend_allowed(void);
+void host_system_suspend_disable(const char *reason);
+
+#else /* !CONFIG_SYSTEM_SUSPEND */
+
+static inline bool host_system_suspend_allowed(void) { return false; }
+static inline void host_system_suspend_disable(const char *reason) {}
+
+#endif
#endif /* ARM_SUSPEND_H */
diff --git a/xen/arch/arm/pci/pci-host-rcar4.c b/xen/arch/arm/pci/pci-host-rcar4.c
index e1e8eb0ee1..0d85ccf4f5 100644
--- a/xen/arch/arm/pci/pci-host-rcar4.c
+++ b/xen/arch/arm/pci/pci-host-rcar4.c
@@ -11,6 +11,7 @@
#include <asm/device.h>
#include <asm/io.h>
#include <asm/pci.h>
+#include <asm/suspend.h>
#include "pci-designware.h"
#include "pci-host-rcar4.h"
@@ -221,6 +222,9 @@ static int __init pci_host_rcar4_probe(struct dt_device_node *dev,
dw_pcie_set_priv(bridge, priv);
dw_pcie_set_version(bridge, RCAR4_DWC_VERSION);
+ host_system_suspend_disable(
+ "R-Car Gen4 PCIe OSID state is not restored");
+
return 0;
err:
xfree(priv);
diff --git a/xen/arch/arm/psci.c b/xen/arch/arm/psci.c
index 294e53a29f..0d2d428a72 100644
--- a/xen/arch/arm/psci.c
+++ b/xen/arch/arm/psci.c
@@ -41,6 +41,13 @@ static bool __ro_after_init has_psci_system_suspend;
#define PSCI_RET(res) ((int32_t)(res).a0)
+#ifdef CONFIG_SYSTEM_SUSPEND
+bool psci_system_suspend_allowed(void)
+{
+ return has_psci_system_suspend;
+}
+#endif
+
int call_psci_cpu_on(int cpu)
{
struct arm_smccc_res res;
diff --git a/xen/arch/arm/suspend.c b/xen/arch/arm/suspend.c
index 6ea4a0f9cc..c7c26bcf03 100644
--- a/xen/arch/arm/suspend.c
+++ b/xen/arch/arm/suspend.c
@@ -1,9 +1,49 @@
/* SPDX-License-Identifier: GPL-2.0-only */
+#include <asm/psci.h>
#include <asm/suspend.h>
+#include <xen/lib.h>
+#include <xen/serial.h>
+
struct resume_cpu_context resume_cpu_context;
+/*
+ * Non-PSCI infrastructure can make host suspend impossible even when the PSCI
+ * SYSTEM_SUSPEND conduit is present, e.g. when a Xen-owned driver has no valid
+ * suspend/resume path.
+ *
+ * This gate is checked only when the last awake control domain attempts to
+ * turn a guest SYSTEM_SUSPEND request into a host-suspend request.
+ */
+static bool __ro_after_init host_system_suspend_runtime_allowed = true;
+
+static bool host_serial_suspend_allowed(void)
+{
+ if ( serial_suspend_supported() )
+ return true;
+
+ printk_once(XENLOG_INFO
+ "Host SYSTEM_SUSPEND blocked: serial unsupported\n");
+
+ return false;
+}
+
+bool host_system_suspend_allowed(void)
+{
+ return psci_system_suspend_allowed() &&
+ host_serial_suspend_allowed() &&
+ host_system_suspend_runtime_allowed;
+}
+
+void host_system_suspend_disable(const char *reason)
+{
+ host_system_suspend_runtime_allowed = false;
+
+ printk(XENLOG_INFO "Host SYSTEM_SUSPEND blocked: %s\n",
+ reason ? reason : "unsupported suspend/resume path");
+}
+
/*
* Local variables:
* mode: C
diff --git a/xen/arch/arm/vpsci.c b/xen/arch/arm/vpsci.c
index 8c7a70c7a9..d42fcd766e 100644
--- a/xen/arch/arm/vpsci.c
+++ b/xen/arch/arm/vpsci.c
@@ -5,6 +5,7 @@
#include <asm/current.h>
#include <asm/domain.h>
+#include <asm/suspend.h>
#include <asm/vgic.h>
#include <asm/vpsci.h>
#include <asm/event.h>
@@ -219,6 +220,95 @@ static void do_psci_0_2_system_reset(void)
domain_shutdown(d,SHUTDOWN_reboot);
}
+/*
+ * Serialise SYSTEM_SUSPEND policy decisions with the domain suspend
+ * transition, so multiple control domains cannot all observe each other as
+ * still awake.
+ */
+static DEFINE_SPINLOCK(vpsci_system_suspend_lock);
+
+static bool domain_in_suspend_state(struct domain *d)
+{
+ bool suspended;
+
+ spin_lock(&d->shutdown_lock);
+ suspended = domain_shutdown_completed(d) &&
+ (d->shutdown_code == SHUTDOWN_suspend);
+ spin_unlock(&d->shutdown_lock);
+
+ return suspended;
+}
+
+static int32_t domain_psci_system_suspend_policy(struct domain *d)
+{
+ struct domain *other;
+ bool last_awake_control_domain = true;
+ bool awake_non_control_domain = false;
+ bool has_control_domain = is_control_domain(d);
+
+ rcu_read_lock(&domlist_read_lock);
+
+ for_each_domain ( other )
+ {
+ bool suspended;
+
+ if ( other == d )
+ continue;
+
+ if ( is_control_domain(other) )
+ has_control_domain = true;
+
+ suspended = domain_in_suspend_state(other);
+ if ( suspended )
+ continue;
+
+ if ( is_control_domain(other) )
+ {
+ last_awake_control_domain = false;
+ break;
+ }
+
+ awake_non_control_domain = true;
+ }
+
+ rcu_read_unlock(&domlist_read_lock);
+
+ /* Non-control domains need a control domain to resume them. */
+ if ( !is_control_domain(d) )
+ return has_control_domain ? 0 : PSCI_DENIED;
+
+ /*
+ * Another control domain is still awake. This request is only the first
+ * phase of the sequencing: park this control domain and leave the host
+ * running. Host-wide suspend gates must not block this intermediate state.
+ */
+ if ( !last_awake_control_domain )
+ return 0;
+
+ /*
+ * This is the last awake control domain. It must not be parked unless the
+ * request can proceed as a host-suspend request; otherwise Xen would lose
+ * the last domain that can coordinate the system suspend.
+ */
+ if ( awake_non_control_domain )
+ {
+ printk(XENLOG_DEBUG
+ "SYSTEM_SUSPEND denied for %pd: non-control domains awake\n",
+ d);
+ return PSCI_DENIED;
+ }
+
+ /*
+ * Host-wide gates are relevant only for the last-control-domain case. They
+ * must not block parking of a non-last control domain, but they must deny
+ * the last control domain when host suspend is not currently available.
+ */
+ if ( !host_system_suspend_allowed() )
+ return PSCI_DENIED;
+
+ return 0;
+}
+
static int32_t do_psci_1_0_system_suspend(register_t epoint, register_t cid)
{
int32_t rc;
@@ -232,10 +322,6 @@ static int32_t do_psci_1_0_system_suspend(register_t epoint, register_t cid)
if ( is_64bit_domain(d) && is_thumb )
return PSCI_INVALID_ADDRESS;
- /* SYSTEM_SUSPEND is not supported for the hardware domain yet */
- if ( is_hardware_domain(d) )
- return PSCI_NOT_SUPPORTED;
-
/* Ensure that all CPUs other than the calling one are offline */
domain_lock(d);
for_each_vcpu ( d, v )
@@ -252,16 +338,29 @@ static int32_t do_psci_1_0_system_suspend(register_t epoint, register_t cid)
if ( rc )
return PSCI_DENIED;
- rc = domain_shutdown(d, SHUTDOWN_suspend);
+ spin_lock(&vpsci_system_suspend_lock);
+
+ rc = domain_psci_system_suspend_policy(d);
+ if ( !rc )
+ {
+ rc = domain_shutdown(d, SHUTDOWN_suspend);
+ if ( rc )
+ rc = PSCI_DENIED;
+ else
+ {
+ rctx->ctxt = ctxt;
+ rctx->wake_cpu = current;
+ }
+ }
+
+ spin_unlock(&vpsci_system_suspend_lock);
+
if ( rc )
{
free_vcpu_guest_context(ctxt);
- return PSCI_DENIED;
+ return rc;
}
- rctx->ctxt = ctxt;
- rctx->wake_cpu = current;
-
gprintk(XENLOG_DEBUG,
"SYSTEM_SUSPEND requested, epoint=%#"PRIregister", cid=%#"PRIregister"\n",
epoint, cid);
@@ -287,10 +386,9 @@ static int32_t do_psci_1_0_features(uint32_t psci_func_id)
case PSCI_0_2_FN32_SYSTEM_RESET:
case PSCI_1_0_FN32_PSCI_FEATURES:
case ARM_SMCCC_VERSION_FID:
- return 0;
case PSCI_1_0_FN32_SYSTEM_SUSPEND:
case PSCI_1_0_FN64_SYSTEM_SUSPEND:
- return is_hardware_domain(current->domain) ? PSCI_NOT_SUPPORTED : 0;
+ return 0;
default:
return PSCI_NOT_SUPPORTED;
}
diff --git a/xen/common/Kconfig b/xen/common/Kconfig
index 5b289e444f..0a3e5d8a93 100644
--- a/xen/common/Kconfig
+++ b/xen/common/Kconfig
@@ -140,6 +140,9 @@ config HAS_EX_TABLE
config HAS_FAST_MULTIPLY
bool
+config HAS_HWDOM_SYSTEM_SUSPEND
+ bool
+
config HAS_IOPORTS
bool
diff --git a/xen/common/domain.c b/xen/common/domain.c
index f3a2634d5f..c56c97dc1d 100644
--- a/xen/common/domain.c
+++ b/xen/common/domain.c
@@ -1377,6 +1377,11 @@ void __domain_crash(struct domain *d)
domain_shutdown(d, SHUTDOWN_crash);
}
+static inline bool want_hwdom_shutdown(uint8_t reason)
+{
+ return !IS_ENABLED(CONFIG_HAS_HWDOM_SYSTEM_SUSPEND) ||
+ reason != SHUTDOWN_suspend;
+}
int domain_shutdown(struct domain *d, u8 reason)
{
@@ -1393,7 +1398,7 @@ int domain_shutdown(struct domain *d, u8 reason)
d->shutdown_code = reason;
reason = d->shutdown_code;
- if ( is_hardware_domain(d) )
+ if ( is_hardware_domain(d) && want_hwdom_shutdown(reason) )
hwdom_shutdown(reason);
if ( domain_shutting_down(d) )
diff --git a/xen/drivers/char/serial.c b/xen/drivers/char/serial.c
index cf0abf1893..95a2fd59c1 100644
--- a/xen/drivers/char/serial.c
+++ b/xen/drivers/char/serial.c
@@ -490,6 +490,8 @@ const struct vuart_info *serial_vuart_info(int idx)
#ifdef CONFIG_SYSTEM_SUSPEND
+static bool __ro_after_init suspend_possible = true;
+
void serial_suspend(void)
{
int i;
@@ -506,6 +508,11 @@ void serial_resume(void)
com[i].driver->resume(&com[i]);
}
+bool serial_suspend_supported(void)
+{
+ return suspend_possible;
+}
+
#endif /* CONFIG_SYSTEM_SUSPEND */
void __init serial_register_uart(int idx, struct uart_driver *driver,
@@ -514,6 +521,11 @@ void __init serial_register_uart(int idx, struct uart_driver *driver,
/* Store UART-specific info. */
com[idx].driver = driver;
com[idx].uart = uart;
+
+#ifdef CONFIG_SYSTEM_SUSPEND
+ if ( !driver->suspend || !driver->resume )
+ suspend_possible = false;
+#endif
}
void __init serial_async_transmit(struct serial_port *port)
diff --git a/xen/drivers/passthrough/arm/iommu.c b/xen/drivers/passthrough/arm/iommu.c
index 100545e23f..461e01703e 100644
--- a/xen/drivers/passthrough/arm/iommu.c
+++ b/xen/drivers/passthrough/arm/iommu.c
@@ -19,6 +19,7 @@
#include <xen/device_tree.h>
#include <xen/iommu.h>
#include <xen/lib.h>
+#include <xen/suspend.h>
#include <asm/device.h>
@@ -46,6 +47,11 @@ void __init iommu_set_ops(const struct iommu_ops *ops)
}
iommu_ops = ops;
+
+#ifdef CONFIG_SYSTEM_SUSPEND
+ if ( !ops->suspend || !ops->resume )
+ host_system_suspend_disable("IOMMU driver lacks suspend support");
+#endif
}
int __init iommu_hardware_setup(void)
diff --git a/xen/drivers/passthrough/arm/smmu-v3.c b/xen/drivers/passthrough/arm/smmu-v3.c
index fa0c57886e..49bdd4dd4f 100644
--- a/xen/drivers/passthrough/arm/smmu-v3.c
+++ b/xen/drivers/passthrough/arm/smmu-v3.c
@@ -91,6 +91,7 @@
#include <asm/io.h>
#include <asm/iommu_fwspec.h>
#include <asm/platform.h>
+#include <asm/suspend.h>
#include "smmu-v3.h"
@@ -1945,6 +1946,7 @@ static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
{
+ static bool __ro_after_init host_suspend_blocked_by_msi;
struct msi_desc *desc;
int ret, nvec = ARM_SMMU_MAX_MSIS;
struct device *dev = smmu->dev;
@@ -1983,6 +1985,13 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
}
}
+ if ( !host_suspend_blocked_by_msi )
+ {
+ host_suspend_blocked_by_msi = true;
+ host_system_suspend_disable(
+ "SMMUv3 MSI IRQ path is unsupported for host suspend");
+ }
+
/* Add callback to free MSIs on teardown */
devm_add_action(dev, arm_smmu_free_msis, dev);
}
diff --git a/xen/include/xen/serial.h b/xen/include/xen/serial.h
index 3a71da767d..4c6f891221 100644
--- a/xen/include/xen/serial.h
+++ b/xen/include/xen/serial.h
@@ -137,6 +137,7 @@ const struct vuart_info* serial_vuart_info(int idx);
/* Serial suspend/resume. */
void serial_suspend(void);
void serial_resume(void);
+bool serial_suspend_supported(void);
#endif
/*
diff --git a/xen/include/xen/suspend.h b/xen/include/xen/suspend.h
index 6f94fd53b0..a941331035 100644
--- a/xen/include/xen/suspend.h
+++ b/xen/include/xen/suspend.h
@@ -6,6 +6,8 @@
#if __has_include(<asm/suspend.h>)
#include <asm/suspend.h>
#else
+struct domain;
+
static inline void arch_domain_resume(struct domain *d) {}
#endif
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v14 15/15] xen/arm: Add host system suspend backend
2026-11-17 1:04 [PATCH v14 00/15] Add initial Xen Suspend-to-RAM support on ARM64 Mykola Kvach
` (13 preceding siblings ...)
2026-11-17 1:05 ` [PATCH v14 14/15] xen/arm: Add vPSCI SYSTEM_SUSPEND policy Mykola Kvach
@ 2026-11-17 1:05 ` Mykola Kvach
2026-11-17 17:05 ` Bertrand Marquis
14 siblings, 1 reply; 20+ messages in thread
From: Mykola Kvach @ 2026-11-17 1:05 UTC (permalink / raw)
To: xen-devel@lists.xenproject.org
Cc: Mykola Kvach, Stefano Stabellini, Julien Grall, Bertrand Marquis,
Michal Orzel, Volodymyr Babchuk
From: Mirela Simonovic <mirela.simonovic@aggios.com>
Add the Xen-wide suspend/resume backend used after a control-domain
vPSCI SYSTEM_SUSPEND request has been accepted. The vPSCI policy,
runtime driver blockers and control-domain sequencing checks are handled
by the preceding commit; this change adds the code that actually drives
the host suspend attempt.
The backend runs from a tasklet scheduled on pCPU0, because non-boot CPUs
are disabled during suspend. It freezes domains, disables the scheduler
and then disables non-boot CPUs.
Host-side suspend participants are handled in phases. IOMMU and console
state are suspended first. Local IRQs are then disabled before suspending
timer and GIC state. On resume or failure, the completed suspend phases
are unwound in reverse: GIC and timer state are restored while IRQs are
still disabled, local IRQs are restored, and then console and IOMMU state
are restored.
On boot, init_ttbr is normally initialized during secondary CPU hotplug.
On uniprocessor systems this can leave init_ttbr uninitialized, so set it
from the boot CPU before entering suspend.
Note: the code is behind CONFIG_HAS_SYSTEM_SUSPEND, which is currently
only selected when UNSUPPORTED is set and MPU is not set.
Signed-off-by: Mirela Simonovic <mirela.simonovic@aggios.com>
Signed-off-by: Saeed Nowshadi <saeed.nowshadi@xilinx.com>
Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
---
Changes in V14:
- Add INFO level to suspend entry and successful resume messages.
- Replace the generic resume status print with a WARNING on suspend
failure after the console has been restored.
- Use warning-level printk() instead of dprintk() for console and PSCI
suspend failures, keeping the details available in release builds.
Changes in V13:
- Explicitly discard console_resume()'s return value. It always returns
zero in the current implementation (MISRA Rule 17.7). No functional
change.
- Remove the redundant rcu_barrier() and its outdated comment before
enable_nonboot_cpus(). Per-CPU areas are kept during suspend, and
cpu_up() already waits for pending RCU callbacks before CPU_UP_PREPARE.
Changes in V10:
- Re-apply boot CPU local errata/workaround handling after SYSTEM_SUSPEND,
before resuming the rest of the host suspend path.
- Move set_init_ttbr() declaration to asm/mmu/mm.h, since it is
MMU-specific.
Changes in V9:
- Split vPSCI availability policy, runtime host-suspend blockers and the
domain-readiness precheck into the preceding commit.
- Trigger the host suspend backend from the control-domain SYSTEM_SUSPEND
path.
- Reorder the host suspend/resume phases so the timer is suspended with
local IRQs disabled and local IRQs are restored after the GIC and timer
resume paths, before the console and IOMMU resume paths.
- Move HAS_HWDOM_SYSTEM_SUSPEND and related logic to policy patch.
Changes in V8:
- Add a pre-suspend check in system_suspend() after scheduler_disable() to
require all domains to be in the shut down state with SHUTDOWN_suspend
before proceeding with the global suspend flow.
- Drop the common-level depends on !ARM_64 || !SYSTEM_SUSPEND from
CONFIG_HAS_HWDOM_SHUTDOWN_ON_SUSPEND and model the ARM64 suspend case
with an arch-selected capability instead.
- Rename CONFIG_HAS_HWDOM_SHUTDOWN_ON_SUSPEND to
CONFIG_HAS_HWDOM_SYSTEM_SUSPEND.
- Rename need_hwdom_shutdown() to want_hwdom_shutdown().
Changes in V7:
- Control domain is responsible for host suspend.
- Add an empty inline host_system_suspend() function when SYSTEM_SUSPEND
config is disabled.
- Use IS_ENABLED() for config checking instead of #ifdef.
- Replace #ifdef checks in domain_shutdown() with IS_ENABLED() to simplify
control flow.
- Factor hardware domain shutdown condition into a helper
(need_hwdom_shutdown()) to avoid preprocessor directives inside the
function.
- Squash with iommu suspend/resume commit.
---
xen/arch/arm/Kconfig | 1 +
xen/arch/arm/cpuerrata.c | 7 +-
xen/arch/arm/include/asm/cpuerrata.h | 1 +
xen/arch/arm/include/asm/mmu/mm.h | 2 +
xen/arch/arm/include/asm/suspend.h | 2 +
xen/arch/arm/mmu/smpboot.c | 2 +-
xen/arch/arm/suspend.c | 152 +++++++++++++++++++++++++++
xen/arch/arm/vpsci.c | 10 +-
8 files changed, 173 insertions(+), 4 deletions(-)
diff --git a/xen/arch/arm/Kconfig b/xen/arch/arm/Kconfig
index fd5f0ddb17..c3e32fb683 100644
--- a/xen/arch/arm/Kconfig
+++ b/xen/arch/arm/Kconfig
@@ -9,6 +9,7 @@ config ARM_64
select 64BIT
select HAS_DOMAIN_TYPE
select HAS_FAST_MULTIPLY
+ select HAS_SYSTEM_SUSPEND if !MPU && UNSUPPORTED
select HAS_VPCI_GUEST_SUPPORT if PCI_PASSTHROUGH
config ARM
diff --git a/xen/arch/arm/cpuerrata.c b/xen/arch/arm/cpuerrata.c
index 35ad98d29d..5a7f127495 100644
--- a/xen/arch/arm/cpuerrata.c
+++ b/xen/arch/arm/cpuerrata.c
@@ -782,6 +782,11 @@ void check_local_cpu_errata(void)
update_cpu_capabilities(arm_errata, "enabled workaround for");
}
+int enable_local_cpu_errata_workarounds(void)
+{
+ return enable_nonboot_cpu_caps(arm_errata);
+}
+
void __init enable_errata_workarounds(void)
{
enable_cpu_capabilities(arm_errata);
@@ -818,7 +823,7 @@ static int cpu_errata_callback(struct notifier_block *nfb,
* fixed to expect an error at CPU_STARTING phase.
*/
ASSERT(system_state != SYS_STATE_boot);
- rc = enable_nonboot_cpu_caps(arm_errata);
+ rc = enable_local_cpu_errata_workarounds();
break;
default:
break;
diff --git a/xen/arch/arm/include/asm/cpuerrata.h b/xen/arch/arm/include/asm/cpuerrata.h
index 1799a16d7e..b93521326f 100644
--- a/xen/arch/arm/include/asm/cpuerrata.h
+++ b/xen/arch/arm/include/asm/cpuerrata.h
@@ -5,6 +5,7 @@
#include <asm/alternative.h>
void check_local_cpu_errata(void);
+int enable_local_cpu_errata_workarounds(void);
void enable_errata_workarounds(void);
#define CHECK_WORKAROUND_HELPER(erratum, feature, arch) \
diff --git a/xen/arch/arm/include/asm/mmu/mm.h b/xen/arch/arm/include/asm/mmu/mm.h
index 7cebc60298..776aef8b1c 100644
--- a/xen/arch/arm/include/asm/mmu/mm.h
+++ b/xen/arch/arm/include/asm/mmu/mm.h
@@ -110,6 +110,8 @@ void dump_pt_walk(paddr_t ttbr, paddr_t addr,
extern void switch_ttbr(uint64_t ttbr);
extern void relocate_and_switch_ttbr(uint64_t ttbr);
+void set_init_ttbr(lpae_t *root);
+
#endif /* __ARM_MMU_MM_H__ */
/*
diff --git a/xen/arch/arm/include/asm/suspend.h b/xen/arch/arm/include/asm/suspend.h
index 50dc6e9fdf..889a6509d9 100644
--- a/xen/arch/arm/include/asm/suspend.h
+++ b/xen/arch/arm/include/asm/suspend.h
@@ -41,11 +41,13 @@ int prepare_resume_ctx(void);
void hyp_resume(void);
bool host_system_suspend_allowed(void);
void host_system_suspend_disable(const char *reason);
+void host_system_suspend(struct domain *d);
#else /* !CONFIG_SYSTEM_SUSPEND */
static inline bool host_system_suspend_allowed(void) { return false; }
static inline void host_system_suspend_disable(const char *reason) {}
+static inline void host_system_suspend(struct domain *d) {}
#endif
diff --git a/xen/arch/arm/mmu/smpboot.c b/xen/arch/arm/mmu/smpboot.c
index 37e91d72b7..ff508ecf40 100644
--- a/xen/arch/arm/mmu/smpboot.c
+++ b/xen/arch/arm/mmu/smpboot.c
@@ -72,7 +72,7 @@ static void clear_boot_pagetables(void)
clear_table(boot_third);
}
-static void set_init_ttbr(lpae_t *root)
+void set_init_ttbr(lpae_t *root)
{
/*
* init_ttbr is part of the identity mapping which is read-only. So
diff --git a/xen/arch/arm/suspend.c b/xen/arch/arm/suspend.c
index c7c26bcf03..815e41242a 100644
--- a/xen/arch/arm/suspend.c
+++ b/xen/arch/arm/suspend.c
@@ -1,10 +1,18 @@
/* SPDX-License-Identifier: GPL-2.0-only */
+#include <asm/cpuerrata.h>
+#include <asm/cpufeature.h>
+#include <asm/gic.h>
#include <asm/psci.h>
#include <asm/suspend.h>
+#include <xen/console.h>
+#include <xen/cpu.h>
+#include <xen/iommu.h>
#include <xen/lib.h>
+#include <xen/sched.h>
#include <xen/serial.h>
+#include <xen/tasklet.h>
struct resume_cpu_context resume_cpu_context;
@@ -44,6 +52,150 @@ void host_system_suspend_disable(const char *reason)
reason ? reason : "unsupported suspend/resume path");
}
+/* Xen suspend. data identifies the domain that initiated suspend. */
+static void system_suspend(void *data)
+{
+ int status;
+ unsigned long flags;
+ struct domain *d = (struct domain *)data;
+
+ BUG_ON(system_state != SYS_STATE_active);
+
+ system_state = SYS_STATE_suspend;
+
+ printk(XENLOG_INFO "Xen suspending...\n");
+
+ freeze_domains();
+ scheduler_disable();
+
+ /*
+ * Non-boot CPUs have to be disabled on suspend and enabled on resume
+ * (hotplug-based mechanism). Disabling non-boot CPUs will lead to PSCI
+ * CPU_OFF to be called by each non-boot CPU. Depending on the underlying
+ * platform capabilities, this may lead to the physical powering down of
+ * CPUs.
+ */
+ status = disable_nonboot_cpus();
+ if ( status )
+ {
+ system_state = SYS_STATE_resume;
+ goto resume_nonboot_cpus;
+ }
+
+ console_start_sync();
+ status = iommu_suspend();
+ if ( status )
+ {
+ system_state = SYS_STATE_resume;
+ goto resume_end_sync;
+ }
+
+ status = console_suspend();
+ if ( status )
+ {
+ printk(XENLOG_WARNING "Failed to suspend the console, err=%d\n", status);
+ system_state = SYS_STATE_resume;
+ goto resume_iommu;
+ }
+
+ local_irq_save(flags);
+
+ time_suspend();
+
+ status = gic_suspend();
+ if ( status )
+ {
+ system_state = SYS_STATE_resume;
+ goto resume_time;
+ }
+
+ set_init_ttbr(xen_pgtable);
+
+ /*
+ * Enable identity mapping before entering suspend to simplify
+ * the resume path
+ */
+ update_boot_mapping(true);
+
+ if ( prepare_resume_ctx() )
+ {
+ status = call_psci_system_suspend();
+ /*
+ * If suspend is finalized properly by above system suspend PSCI call,
+ * the code below in this 'if' branch will never execute. Execution
+ * will continue from hyp_resume which is the hypervisor's resume point.
+ * In hyp_resume CPU context will be restored and since link-register is
+ * restored as well, it will appear to return from prepare_resume_ctx.
+ * The difference in returning from prepare_resume_ctx on system suspend
+ * versus resume is in function's return value: on suspend, the return
+ * value is a non-zero value, on resume it is zero. That is why the
+ * control flow will not re-enter this 'if' branch on resume.
+ */
+ if ( status )
+ printk(XENLOG_WARNING "PSCI system suspend failed, err=%d\n",
+ status);
+
+ system_state = SYS_STATE_resume;
+ }
+ else
+ {
+ system_state = SYS_STATE_resume;
+
+ /*
+ * CPU0 resumes directly from hyp_resume(), bypassing the CPU hotplug
+ * path that re-checks and re-enables errata workarounds for secondary
+ * CPUs.
+ */
+ check_local_cpu_errata();
+ check_local_cpu_features();
+ BUG_ON(enable_local_cpu_errata_workarounds());
+ }
+
+ update_boot_mapping(false);
+
+ gic_resume();
+
+ resume_time:
+ time_resume();
+
+ local_irq_restore(flags);
+
+ (void)console_resume();
+
+ resume_iommu:
+ iommu_resume();
+
+ resume_end_sync:
+ console_end_sync();
+
+ resume_nonboot_cpus:
+ enable_nonboot_cpus();
+
+ scheduler_enable();
+ thaw_domains();
+
+ system_state = SYS_STATE_active;
+
+ if ( status )
+ printk(XENLOG_WARNING "System suspend failed: %d\n", status);
+ else
+ printk(XENLOG_INFO "Xen resumed\n");
+
+ domain_resume(d);
+}
+
+static DECLARE_TASKLET(system_suspend_tasklet, system_suspend, NULL);
+
+void host_system_suspend(struct domain *d)
+{
+ system_suspend_tasklet.data = (void *)d;
+ /*
+ * The suspend procedure has to be finalized by the pCPU#0 (non-boot pCPUs
+ * will be disabled during the suspend).
+ */
+ tasklet_schedule_on_cpu(&system_suspend_tasklet, 0);
+}
+
/*
* Local variables:
* mode: C
diff --git a/xen/arch/arm/vpsci.c b/xen/arch/arm/vpsci.c
index d42fcd766e..bcd4a9ae8d 100644
--- a/xen/arch/arm/vpsci.c
+++ b/xen/arch/arm/vpsci.c
@@ -239,7 +239,8 @@ static bool domain_in_suspend_state(struct domain *d)
return suspended;
}
-static int32_t domain_psci_system_suspend_policy(struct domain *d)
+static int32_t domain_psci_system_suspend_policy(struct domain *d,
+ bool *host_suspend)
{
struct domain *other;
bool last_awake_control_domain = true;
@@ -306,6 +307,7 @@ static int32_t domain_psci_system_suspend_policy(struct domain *d)
if ( !host_system_suspend_allowed() )
return PSCI_DENIED;
+ *host_suspend = true;
return 0;
}
@@ -316,6 +318,7 @@ static int32_t do_psci_1_0_system_suspend(register_t epoint, register_t cid)
struct vcpu *v;
struct domain *d = current->domain;
bool is_thumb = epoint & 1;
+ bool host_suspend = false;
struct resume_info *rctx = &d->arch.resume_ctx;
/* THUMB set is not allowed with 64-bit domain */
@@ -340,7 +343,7 @@ static int32_t do_psci_1_0_system_suspend(register_t epoint, register_t cid)
spin_lock(&vpsci_system_suspend_lock);
- rc = domain_psci_system_suspend_policy(d);
+ rc = domain_psci_system_suspend_policy(d, &host_suspend);
if ( !rc )
{
rc = domain_shutdown(d, SHUTDOWN_suspend);
@@ -365,6 +368,9 @@ static int32_t do_psci_1_0_system_suspend(register_t epoint, register_t cid)
"SYSTEM_SUSPEND requested, epoint=%#"PRIregister", cid=%#"PRIregister"\n",
epoint, cid);
+ if ( host_suspend )
+ host_system_suspend(d);
+
return rc;
}
--
2.53.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* Re: [PATCH v14 15/15] xen/arm: Add host system suspend backend
2026-11-17 1:05 ` [PATCH v14 15/15] xen/arm: Add host system suspend backend Mykola Kvach
@ 2026-11-17 17:05 ` Bertrand Marquis
0 siblings, 0 replies; 20+ messages in thread
From: Bertrand Marquis @ 2026-11-17 17:05 UTC (permalink / raw)
To: Mykola Kvach
Cc: xen-devel@lists.xenproject.org, Stefano Stabellini, Julien Grall,
Michal Orzel, Volodymyr Babchuk
Hi Mykola,
> On 17 Nov 2026, at 02:05, Mykola Kvach <mykola_kvach@epam.com> wrote:
>
> From: Mirela Simonovic <mirela.simonovic@aggios.com>
>
> Add the Xen-wide suspend/resume backend used after a control-domain
> vPSCI SYSTEM_SUSPEND request has been accepted. The vPSCI policy,
> runtime driver blockers and control-domain sequencing checks are handled
> by the preceding commit; this change adds the code that actually drives
> the host suspend attempt.
>
> The backend runs from a tasklet scheduled on pCPU0, because non-boot CPUs
> are disabled during suspend. It freezes domains, disables the scheduler
> and then disables non-boot CPUs.
>
> Host-side suspend participants are handled in phases. IOMMU and console
> state are suspended first. Local IRQs are then disabled before suspending
> timer and GIC state. On resume or failure, the completed suspend phases
> are unwound in reverse: GIC and timer state are restored while IRQs are
> still disabled, local IRQs are restored, and then console and IOMMU state
> are restored.
>
> On boot, init_ttbr is normally initialized during secondary CPU hotplug.
> On uniprocessor systems this can leave init_ttbr uninitialized, so set it
> from the boot CPU before entering suspend.
>
> Note: the code is behind CONFIG_HAS_SYSTEM_SUSPEND, which is currently
> only selected when UNSUPPORTED is set and MPU is not set.
>
> Signed-off-by: Mirela Simonovic <mirela.simonovic@aggios.com>
> Signed-off-by: Saeed Nowshadi <saeed.nowshadi@xilinx.com>
> Signed-off-by: Mykyta Poturai <mykyta_poturai@epam.com>
> Signed-off-by: Mykola Kvach <mykola_kvach@epam.com>
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
Cheers
Bertrand
> ---
> Changes in V14:
> - Add INFO level to suspend entry and successful resume messages.
> - Replace the generic resume status print with a WARNING on suspend
> failure after the console has been restored.
> - Use warning-level printk() instead of dprintk() for console and PSCI
> suspend failures, keeping the details available in release builds.
>
> Changes in V13:
> - Explicitly discard console_resume()'s return value. It always returns
> zero in the current implementation (MISRA Rule 17.7). No functional
> change.
> - Remove the redundant rcu_barrier() and its outdated comment before
> enable_nonboot_cpus(). Per-CPU areas are kept during suspend, and
> cpu_up() already waits for pending RCU callbacks before CPU_UP_PREPARE.
>
> Changes in V10:
> - Re-apply boot CPU local errata/workaround handling after SYSTEM_SUSPEND,
> before resuming the rest of the host suspend path.
> - Move set_init_ttbr() declaration to asm/mmu/mm.h, since it is
> MMU-specific.
>
> Changes in V9:
> - Split vPSCI availability policy, runtime host-suspend blockers and the
> domain-readiness precheck into the preceding commit.
> - Trigger the host suspend backend from the control-domain SYSTEM_SUSPEND
> path.
> - Reorder the host suspend/resume phases so the timer is suspended with
> local IRQs disabled and local IRQs are restored after the GIC and timer
> resume paths, before the console and IOMMU resume paths.
> - Move HAS_HWDOM_SYSTEM_SUSPEND and related logic to policy patch.
>
> Changes in V8:
> - Add a pre-suspend check in system_suspend() after scheduler_disable() to
> require all domains to be in the shut down state with SHUTDOWN_suspend
> before proceeding with the global suspend flow.
> - Drop the common-level depends on !ARM_64 || !SYSTEM_SUSPEND from
> CONFIG_HAS_HWDOM_SHUTDOWN_ON_SUSPEND and model the ARM64 suspend case
> with an arch-selected capability instead.
> - Rename CONFIG_HAS_HWDOM_SHUTDOWN_ON_SUSPEND to
> CONFIG_HAS_HWDOM_SYSTEM_SUSPEND.
> - Rename need_hwdom_shutdown() to want_hwdom_shutdown().
>
> Changes in V7:
> - Control domain is responsible for host suspend.
> - Add an empty inline host_system_suspend() function when SYSTEM_SUSPEND
> config is disabled.
> - Use IS_ENABLED() for config checking instead of #ifdef.
> - Replace #ifdef checks in domain_shutdown() with IS_ENABLED() to simplify
> control flow.
> - Factor hardware domain shutdown condition into a helper
> (need_hwdom_shutdown()) to avoid preprocessor directives inside the
> function.
> - Squash with iommu suspend/resume commit.
> ---
> xen/arch/arm/Kconfig | 1 +
> xen/arch/arm/cpuerrata.c | 7 +-
> xen/arch/arm/include/asm/cpuerrata.h | 1 +
> xen/arch/arm/include/asm/mmu/mm.h | 2 +
> xen/arch/arm/include/asm/suspend.h | 2 +
> xen/arch/arm/mmu/smpboot.c | 2 +-
> xen/arch/arm/suspend.c | 152 +++++++++++++++++++++++++++
> xen/arch/arm/vpsci.c | 10 +-
> 8 files changed, 173 insertions(+), 4 deletions(-)
>
> diff --git a/xen/arch/arm/Kconfig b/xen/arch/arm/Kconfig
> index fd5f0ddb17..c3e32fb683 100644
> --- a/xen/arch/arm/Kconfig
> +++ b/xen/arch/arm/Kconfig
> @@ -9,6 +9,7 @@ config ARM_64
> select 64BIT
> select HAS_DOMAIN_TYPE
> select HAS_FAST_MULTIPLY
> + select HAS_SYSTEM_SUSPEND if !MPU && UNSUPPORTED
> select HAS_VPCI_GUEST_SUPPORT if PCI_PASSTHROUGH
>
> config ARM
> diff --git a/xen/arch/arm/cpuerrata.c b/xen/arch/arm/cpuerrata.c
> index 35ad98d29d..5a7f127495 100644
> --- a/xen/arch/arm/cpuerrata.c
> +++ b/xen/arch/arm/cpuerrata.c
> @@ -782,6 +782,11 @@ void check_local_cpu_errata(void)
> update_cpu_capabilities(arm_errata, "enabled workaround for");
> }
>
> +int enable_local_cpu_errata_workarounds(void)
> +{
> + return enable_nonboot_cpu_caps(arm_errata);
> +}
> +
> void __init enable_errata_workarounds(void)
> {
> enable_cpu_capabilities(arm_errata);
> @@ -818,7 +823,7 @@ static int cpu_errata_callback(struct notifier_block *nfb,
> * fixed to expect an error at CPU_STARTING phase.
> */
> ASSERT(system_state != SYS_STATE_boot);
> - rc = enable_nonboot_cpu_caps(arm_errata);
> + rc = enable_local_cpu_errata_workarounds();
> break;
> default:
> break;
> diff --git a/xen/arch/arm/include/asm/cpuerrata.h b/xen/arch/arm/include/asm/cpuerrata.h
> index 1799a16d7e..b93521326f 100644
> --- a/xen/arch/arm/include/asm/cpuerrata.h
> +++ b/xen/arch/arm/include/asm/cpuerrata.h
> @@ -5,6 +5,7 @@
> #include <asm/alternative.h>
>
> void check_local_cpu_errata(void);
> +int enable_local_cpu_errata_workarounds(void);
> void enable_errata_workarounds(void);
>
> #define CHECK_WORKAROUND_HELPER(erratum, feature, arch) \
> diff --git a/xen/arch/arm/include/asm/mmu/mm.h b/xen/arch/arm/include/asm/mmu/mm.h
> index 7cebc60298..776aef8b1c 100644
> --- a/xen/arch/arm/include/asm/mmu/mm.h
> +++ b/xen/arch/arm/include/asm/mmu/mm.h
> @@ -110,6 +110,8 @@ void dump_pt_walk(paddr_t ttbr, paddr_t addr,
> extern void switch_ttbr(uint64_t ttbr);
> extern void relocate_and_switch_ttbr(uint64_t ttbr);
>
> +void set_init_ttbr(lpae_t *root);
> +
> #endif /* __ARM_MMU_MM_H__ */
>
> /*
> diff --git a/xen/arch/arm/include/asm/suspend.h b/xen/arch/arm/include/asm/suspend.h
> index 50dc6e9fdf..889a6509d9 100644
> --- a/xen/arch/arm/include/asm/suspend.h
> +++ b/xen/arch/arm/include/asm/suspend.h
> @@ -41,11 +41,13 @@ int prepare_resume_ctx(void);
> void hyp_resume(void);
> bool host_system_suspend_allowed(void);
> void host_system_suspend_disable(const char *reason);
> +void host_system_suspend(struct domain *d);
>
> #else /* !CONFIG_SYSTEM_SUSPEND */
>
> static inline bool host_system_suspend_allowed(void) { return false; }
> static inline void host_system_suspend_disable(const char *reason) {}
> +static inline void host_system_suspend(struct domain *d) {}
>
> #endif
>
> diff --git a/xen/arch/arm/mmu/smpboot.c b/xen/arch/arm/mmu/smpboot.c
> index 37e91d72b7..ff508ecf40 100644
> --- a/xen/arch/arm/mmu/smpboot.c
> +++ b/xen/arch/arm/mmu/smpboot.c
> @@ -72,7 +72,7 @@ static void clear_boot_pagetables(void)
> clear_table(boot_third);
> }
>
> -static void set_init_ttbr(lpae_t *root)
> +void set_init_ttbr(lpae_t *root)
> {
> /*
> * init_ttbr is part of the identity mapping which is read-only. So
> diff --git a/xen/arch/arm/suspend.c b/xen/arch/arm/suspend.c
> index c7c26bcf03..815e41242a 100644
> --- a/xen/arch/arm/suspend.c
> +++ b/xen/arch/arm/suspend.c
> @@ -1,10 +1,18 @@
> /* SPDX-License-Identifier: GPL-2.0-only */
>
> +#include <asm/cpuerrata.h>
> +#include <asm/cpufeature.h>
> +#include <asm/gic.h>
> #include <asm/psci.h>
> #include <asm/suspend.h>
>
> +#include <xen/console.h>
> +#include <xen/cpu.h>
> +#include <xen/iommu.h>
> #include <xen/lib.h>
> +#include <xen/sched.h>
> #include <xen/serial.h>
> +#include <xen/tasklet.h>
>
> struct resume_cpu_context resume_cpu_context;
>
> @@ -44,6 +52,150 @@ void host_system_suspend_disable(const char *reason)
> reason ? reason : "unsupported suspend/resume path");
> }
>
> +/* Xen suspend. data identifies the domain that initiated suspend. */
> +static void system_suspend(void *data)
> +{
> + int status;
> + unsigned long flags;
> + struct domain *d = (struct domain *)data;
> +
> + BUG_ON(system_state != SYS_STATE_active);
> +
> + system_state = SYS_STATE_suspend;
> +
> + printk(XENLOG_INFO "Xen suspending...\n");
> +
> + freeze_domains();
> + scheduler_disable();
> +
> + /*
> + * Non-boot CPUs have to be disabled on suspend and enabled on resume
> + * (hotplug-based mechanism). Disabling non-boot CPUs will lead to PSCI
> + * CPU_OFF to be called by each non-boot CPU. Depending on the underlying
> + * platform capabilities, this may lead to the physical powering down of
> + * CPUs.
> + */
> + status = disable_nonboot_cpus();
> + if ( status )
> + {
> + system_state = SYS_STATE_resume;
> + goto resume_nonboot_cpus;
> + }
> +
> + console_start_sync();
> + status = iommu_suspend();
> + if ( status )
> + {
> + system_state = SYS_STATE_resume;
> + goto resume_end_sync;
> + }
> +
> + status = console_suspend();
> + if ( status )
> + {
> + printk(XENLOG_WARNING "Failed to suspend the console, err=%d\n", status);
> + system_state = SYS_STATE_resume;
> + goto resume_iommu;
> + }
> +
> + local_irq_save(flags);
> +
> + time_suspend();
> +
> + status = gic_suspend();
> + if ( status )
> + {
> + system_state = SYS_STATE_resume;
> + goto resume_time;
> + }
> +
> + set_init_ttbr(xen_pgtable);
> +
> + /*
> + * Enable identity mapping before entering suspend to simplify
> + * the resume path
> + */
> + update_boot_mapping(true);
> +
> + if ( prepare_resume_ctx() )
> + {
> + status = call_psci_system_suspend();
> + /*
> + * If suspend is finalized properly by above system suspend PSCI call,
> + * the code below in this 'if' branch will never execute. Execution
> + * will continue from hyp_resume which is the hypervisor's resume point.
> + * In hyp_resume CPU context will be restored and since link-register is
> + * restored as well, it will appear to return from prepare_resume_ctx.
> + * The difference in returning from prepare_resume_ctx on system suspend
> + * versus resume is in function's return value: on suspend, the return
> + * value is a non-zero value, on resume it is zero. That is why the
> + * control flow will not re-enter this 'if' branch on resume.
> + */
> + if ( status )
> + printk(XENLOG_WARNING "PSCI system suspend failed, err=%d\n",
> + status);
> +
> + system_state = SYS_STATE_resume;
> + }
> + else
> + {
> + system_state = SYS_STATE_resume;
> +
> + /*
> + * CPU0 resumes directly from hyp_resume(), bypassing the CPU hotplug
> + * path that re-checks and re-enables errata workarounds for secondary
> + * CPUs.
> + */
> + check_local_cpu_errata();
> + check_local_cpu_features();
> + BUG_ON(enable_local_cpu_errata_workarounds());
> + }
> +
> + update_boot_mapping(false);
> +
> + gic_resume();
> +
> + resume_time:
> + time_resume();
> +
> + local_irq_restore(flags);
> +
> + (void)console_resume();
> +
> + resume_iommu:
> + iommu_resume();
> +
> + resume_end_sync:
> + console_end_sync();
> +
> + resume_nonboot_cpus:
> + enable_nonboot_cpus();
> +
> + scheduler_enable();
> + thaw_domains();
> +
> + system_state = SYS_STATE_active;
> +
> + if ( status )
> + printk(XENLOG_WARNING "System suspend failed: %d\n", status);
> + else
> + printk(XENLOG_INFO "Xen resumed\n");
> +
> + domain_resume(d);
> +}
> +
> +static DECLARE_TASKLET(system_suspend_tasklet, system_suspend, NULL);
> +
> +void host_system_suspend(struct domain *d)
> +{
> + system_suspend_tasklet.data = (void *)d;
> + /*
> + * The suspend procedure has to be finalized by the pCPU#0 (non-boot pCPUs
> + * will be disabled during the suspend).
> + */
> + tasklet_schedule_on_cpu(&system_suspend_tasklet, 0);
> +}
> +
> /*
> * Local variables:
> * mode: C
> diff --git a/xen/arch/arm/vpsci.c b/xen/arch/arm/vpsci.c
> index d42fcd766e..bcd4a9ae8d 100644
> --- a/xen/arch/arm/vpsci.c
> +++ b/xen/arch/arm/vpsci.c
> @@ -239,7 +239,8 @@ static bool domain_in_suspend_state(struct domain *d)
> return suspended;
> }
>
> -static int32_t domain_psci_system_suspend_policy(struct domain *d)
> +static int32_t domain_psci_system_suspend_policy(struct domain *d,
> + bool *host_suspend)
> {
> struct domain *other;
> bool last_awake_control_domain = true;
> @@ -306,6 +307,7 @@ static int32_t domain_psci_system_suspend_policy(struct domain *d)
> if ( !host_system_suspend_allowed() )
> return PSCI_DENIED;
>
> + *host_suspend = true;
> return 0;
> }
>
> @@ -316,6 +318,7 @@ static int32_t do_psci_1_0_system_suspend(register_t epoint, register_t cid)
> struct vcpu *v;
> struct domain *d = current->domain;
> bool is_thumb = epoint & 1;
> + bool host_suspend = false;
> struct resume_info *rctx = &d->arch.resume_ctx;
>
> /* THUMB set is not allowed with 64-bit domain */
> @@ -340,7 +343,7 @@ static int32_t do_psci_1_0_system_suspend(register_t epoint, register_t cid)
>
> spin_lock(&vpsci_system_suspend_lock);
>
> - rc = domain_psci_system_suspend_policy(d);
> + rc = domain_psci_system_suspend_policy(d, &host_suspend);
> if ( !rc )
> {
> rc = domain_shutdown(d, SHUTDOWN_suspend);
> @@ -365,6 +368,9 @@ static int32_t do_psci_1_0_system_suspend(register_t epoint, register_t cid)
> "SYSTEM_SUSPEND requested, epoint=%#"PRIregister", cid=%#"PRIregister"\n",
> epoint, cid);
>
> + if ( host_suspend )
> + host_system_suspend(d);
> +
> return rc;
> }
>
> --
> 2.53.0
^ permalink raw reply [flat|nested] 20+ messages in thread