From 63f13483f0689a4de20fbfd847866ab39bec736f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Apr 2022 19:38:57 +0100 Subject: [PATCH] irqchip/gic-v3: Relax polling of GIC{R,D}_CTLR.RWP Recent work on the KVM GIC emulation has revealed that the GICv3 driver is a bit RWP-happy, as it polls this bit for each and every write MMIO access involving a single interrupt. As it turns out, polling RWP is only required when: - Disabling an SGI, PPI or SPI - Disabling LPIs at the redistributor level - Disabling groups - Enabling ARE - Dealing with DPG* Simplify the driver by removing all the other instances of RWP polling, and add the one that was missing when enabling the distributor (as that's where we set ARE). Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220405183857.205960-4-maz@kernel.org --- drivers/irqchip/irq-gic-v3.c | 38 +++++++++++++++++------------------- 1 file changed, 18 insertions(+), 20 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index f98651ed4e62..b8026847e787 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -352,28 +352,27 @@ static int gic_peek_irq(struct irq_data *d, u32 offset) static void gic_poke_irq(struct irq_data *d, u32 offset) { - void (*rwp_wait)(void); void __iomem *base; u32 index, mask; offset = convert_offset_index(d, offset, &index); mask = 1 << (index % 32); - if (gic_irq_in_rdist(d)) { + if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); - rwp_wait = gic_redist_wait_for_rwp; - } else { + else base = gic_data.dist_base; - rwp_wait = gic_dist_wait_for_rwp; - } writel_relaxed(mask, base + offset + (index / 32) * 4); - rwp_wait(); } static void gic_mask_irq(struct irq_data *d) { gic_poke_irq(d, GICD_ICENABLER); + if (gic_irq_in_rdist(d)) + gic_redist_wait_for_rwp(); + else + gic_dist_wait_for_rwp(); } static void gic_eoimode1_mask_irq(struct irq_data *d) @@ -420,7 +419,11 @@ static int gic_irq_set_irqchip_state(struct irq_data *d, break; case IRQCHIP_STATE_MASKED: - reg = val ? GICD_ICENABLER : GICD_ISENABLER; + if (val) { + gic_mask_irq(d); + return 0; + } + reg = GICD_ISENABLER; break; default: @@ -574,7 +577,6 @@ static int gic_set_type(struct irq_data *d, unsigned int type) { enum gic_intid_range range; unsigned int irq = gic_irq(d); - void (*rwp_wait)(void); void __iomem *base; u32 offset, index; int ret; @@ -590,17 +592,14 @@ static int gic_set_type(struct irq_data *d, unsigned int type) type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING) return -EINVAL; - if (gic_irq_in_rdist(d)) { + if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); - rwp_wait = gic_redist_wait_for_rwp; - } else { + else base = gic_data.dist_base; - rwp_wait = gic_dist_wait_for_rwp; - } offset = convert_offset_index(d, GICD_ICFGR, &index); - ret = gic_configure_irq(index, type, base + offset, rwp_wait); + ret = gic_configure_irq(index, type, base + offset, NULL); if (ret && (range == PPI_RANGE || range == EPPI_RANGE)) { /* Misconfigured PPIs are usually not fatal */ pr_warn("GIC: PPI INTID%d is secure or misconfigured\n", irq); @@ -807,8 +806,8 @@ static void __init gic_dist_init(void) for (i = 0; i < GIC_ESPI_NR; i += 4) writel_relaxed(GICD_INT_DEF_PRI_X4, base + GICD_IPRIORITYRnE + i); - /* Now do the common stuff, and wait for the distributor to drain */ - gic_dist_config(base, GIC_LINE_NR, gic_dist_wait_for_rwp); + /* Now do the common stuff */ + gic_dist_config(base, GIC_LINE_NR, NULL); val = GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1; if (gic_data.rdists.gicd_typer2 & GICD_TYPER2_nASSGIcap) { @@ -816,8 +815,9 @@ static void __init gic_dist_init(void) val |= GICD_CTLR_nASSGIreq; } - /* Enable distributor with ARE, Group1 */ + /* Enable distributor with ARE, Group1, and wait for it to drain */ writel_relaxed(val, base + GICD_CTLR); + gic_dist_wait_for_rwp(); /* * Set all global interrupts to the boot CPU only. ARE must be @@ -1298,8 +1298,6 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, */ if (enabled) gic_unmask_irq(d); - else - gic_dist_wait_for_rwp(); irq_data_update_effective_affinity(d, cpumask_of(cpu));