Merge tag 'powerpc-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Switch to the generic C VDSO, as well as some cleanups of our VDSO
   setup/handling code.

 - Support for KUAP (Kernel User Access Prevention) on systems using the
   hashed page table MMU, using memory protection keys.

 - Better handling of PowerVM SMT8 systems where all threads of a core
   do not share an L2, allowing the scheduler to make better scheduling
   decisions.

 - Further improvements to our machine check handling.

 - Show registers when unwinding interrupt frames during stack traces.

 - Improvements to our pseries (PowerVM) partition migration code.

 - Several series from Christophe refactoring and cleaning up various
   parts of the 32-bit code.

 - Other smaller features, fixes & cleanups.

Thanks to: Alan Modra, Alexey Kardashevskiy, Andrew Donnellan, Aneesh
Kumar K.V, Ard Biesheuvel, Athira Rajeev, Balamuruhan S, Bill Wendling,
Cédric Le Goater, Christophe Leroy, Christophe Lombard, Colin Ian King,
Daniel Axtens, David Hildenbrand, Frederic Barrat, Ganesh Goudar,
Gautham R. Shenoy, Geert Uytterhoeven, Giuseppe Sacco, Greg Kurz,
Harish, Jan Kratochvil, Jordan Niethe, Kaixu Xia, Laurent Dufour,
Leonardo Bras, Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu
Desnoyers, Nathan Lynch, Nicholas Piggin, Oleg Nesterov, Oliver
O'Halloran, Oscar Salvador, Po-Hsu Lin, Qian Cai, Qinglang Miao, Randy
Dunlap, Ravi Bangoria, Sachin Sant, Sandipan Das, Sebastian Andrzej
Siewior , Segher Boessenkool, Srikar Dronamraju, Tyrel Datwyler, Uwe
Kleine-König, Vincent Stehlé, Youling Tang, and Zhang Xiaoxu.

* tag 'powerpc-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (304 commits)
  powerpc/32s: Fix cleanup_cpu_mmu_context() compile bug
  powerpc: Add config fragment for disabling -Werror
  powerpc/configs: Add ppc64le_allnoconfig target
  powerpc/powernv: Rate limit opal-elog read failure message
  powerpc/pseries/memhotplug: Quieten some DLPAR operations
  powerpc/ps3: use dma_mapping_error()
  powerpc: force inlining of csum_partial() to avoid multiple csum_partial() with GCC10
  powerpc/perf: Fix Threshold Event Counter Multiplier width for P10
  powerpc/mm: Fix hugetlb_free_pmd_range() and hugetlb_free_pud_range()
  KVM: PPC: Book3S HV: Fix mask size for emulated msgsndp
  KVM: PPC: fix comparison to bool warning
  KVM: PPC: Book3S: Assign boolean values to a bool variable
  powerpc: Inline setup_kup()
  powerpc/64s: Mark the kuap/kuep functions non __init
  KVM: PPC: Book3S HV: XIVE: Add a comment regarding VP numbering
  powerpc/xive: Improve error reporting of OPAL calls
  powerpc/xive: Simplify xive_do_source_eoi()
  powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_EOI_FW
  powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_MASK_FW
  powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_SHIFT_BUG
  ...

1 files changed, 73 insertions, 61 deletions

diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index a0ebc29f30b2..30dfeac731c6 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -219,7 +219,7 @@ int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
 	/* In single escalation mode, we grab the ESB MMIO of the
 	 * interrupt and mask it. Also populate the VCPU v/raddr
 	 * of the ESB page for use by asm entry/exit code. Finally
-	 * set the XIVE_IRQ_NO_EOI flag which will prevent the
+	 * set the XIVE_IRQ_FLAG_NO_EOI flag which will prevent the
 	 * core code from performing an EOI on the escalation
 	 * interrupt, thus leaving it effectively masked after
 	 * it fires once.
@@ -231,7 +231,7 @@ int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
 		xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01);
 		vcpu->arch.xive_esc_raddr = xd->eoi_page;
 		vcpu->arch.xive_esc_vaddr = (__force u64)xd->eoi_mmio;
-		xd->flags |= XIVE_IRQ_NO_EOI;
+		xd->flags |= XIVE_IRQ_FLAG_NO_EOI;
 	}
 
 	return 0;
@@ -419,37 +419,16 @@ static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
 	/* Get the right irq */
 	kvmppc_xive_select_irq(state, &hw_num, &xd);
 
+	/* Set PQ to 10, return old P and old Q and remember them */
+	val = xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_10);
+	state->old_p = !!(val & 2);
+	state->old_q = !!(val & 1);
+
 	/*
-	 * If the interrupt is marked as needing masking via
-	 * firmware, we do it here. Firmware masking however
-	 * is "lossy", it won't return the old p and q bits
-	 * and won't set the interrupt to a state where it will
-	 * record queued ones. If this is an issue we should do
-	 * lazy masking instead.
-	 *
-	 * For now, we work around this in unmask by forcing
-	 * an interrupt whenever we unmask a non-LSI via FW
-	 * (if ever).
+	 * Synchronize hardware to sensure the queues are updated when
+	 * masking
 	 */
-	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
-		xive_native_configure_irq(hw_num,
-				kvmppc_xive_vp(xive, state->act_server),
-				MASKED, state->number);
-		/* set old_p so we can track if an H_EOI was done */
-		state->old_p = true;
-		state->old_q = false;
-	} else {
-		/* Set PQ to 10, return old P and old Q and remember them */
-		val = xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_10);
-		state->old_p = !!(val & 2);
-		state->old_q = !!(val & 1);
-
-		/*
-		 * Synchronize hardware to sensure the queues are updated
-		 * when masking
-		 */
-		xive_native_sync_source(hw_num);
-	}
+	xive_native_sync_source(hw_num);
 
 	return old_prio;
 }
@@ -483,23 +462,6 @@ static void xive_finish_unmask(struct kvmppc_xive *xive,
 	/* Get the right irq */
 	kvmppc_xive_select_irq(state, &hw_num, &xd);
 
-	/*
-	 * See comment in xive_lock_and_mask() concerning masking
-	 * via firmware.
-	 */
-	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
-		xive_native_configure_irq(hw_num,
-				kvmppc_xive_vp(xive, state->act_server),
-				state->act_priority, state->number);
-		/* If an EOI is needed, do it here */
-		if (!state->old_p)
-			xive_vm_source_eoi(hw_num, xd);
-		/* If this is not an LSI, force a trigger */
-		if (!(xd->flags & OPAL_XIVE_IRQ_LSI))
-			xive_irq_trigger(xd);
-		goto bail;
-	}
-
 	/* Old Q set, set PQ to 11 */
 	if (state->old_q)
 		xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_11);
@@ -2125,9 +2087,8 @@ int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu)
 		if (!q->qpage && !xc->esc_virq[i])
 			continue;
 
-		seq_printf(m, " [q%d]: ", i);
-
 		if (q->qpage) {
+			seq_printf(m, "    q[%d]: ", i);
 			idx = q->idx;
 			i0 = be32_to_cpup(q->qpage + idx);
 			idx = (idx + 1) & q->msk;
@@ -2141,16 +2102,54 @@ int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu)
 				irq_data_get_irq_handler_data(d);
 			u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
 
-			seq_printf(m, "E:%c%c I(%d:%llx:%llx)",
-				   (pq & XIVE_ESB_VAL_P) ? 'P' : 'p',
-				   (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q',
-				   xc->esc_virq[i], pq, xd->eoi_page);
+			seq_printf(m, "    ESC %d %c%c EOI @%llx",
+				   xc->esc_virq[i],
+				   (pq & XIVE_ESB_VAL_P) ? 'P' : '-',
+				   (pq & XIVE_ESB_VAL_Q) ? 'Q' : '-',
+				   xd->eoi_page);
 			seq_puts(m, "\n");
 		}
 	}
 	return 0;
 }
 
+void kvmppc_xive_debug_show_sources(struct seq_file *m,
+				    struct kvmppc_xive_src_block *sb)
+{
+	int i;
+
+	seq_puts(m, "    LISN      HW/CHIP   TYPE    PQ      EISN    CPU/PRIO\n");
+	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
+		struct kvmppc_xive_irq_state *state = &sb->irq_state[i];
+		struct xive_irq_data *xd;
+		u64 pq;
+		u32 hw_num;
+
+		if (!state->valid)
+			continue;
+
+		kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+		pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
+
+		seq_printf(m, "%08x  %08x/%02x", state->number, hw_num,
+			   xd->src_chip);
+		if (state->lsi)
+			seq_printf(m, " %cLSI", state->asserted ? '^' : ' ');
+		else
+			seq_puts(m, "  MSI");
+
+		seq_printf(m, " %s  %c%c  %08x   % 4d/%d",
+			   state->ipi_number == hw_num ? "IPI" : " PT",
+			   pq & XIVE_ESB_VAL_P ? 'P' : '-',
+			   pq & XIVE_ESB_VAL_Q ? 'Q' : '-',
+			   state->eisn, state->act_server,
+			   state->act_priority);
+
+		seq_puts(m, "\n");
+	}
+}
+
 static int xive_debug_show(struct seq_file *m, void *private)
 {
 	struct kvmppc_xive *xive = m->private;
@@ -2171,7 +2170,7 @@ static int xive_debug_show(struct seq_file *m, void *private)
 	if (!kvm)
 		return 0;
 
-	seq_printf(m, "=========\nVCPU state\n=========\n");
+	seq_puts(m, "=========\nVCPU state\n=========\n");
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
@@ -2179,11 +2178,12 @@ static int xive_debug_show(struct seq_file *m, void *private)
 		if (!xc)
 			continue;
 
-		seq_printf(m, "cpu server %#x VP:%#x CPPR:%#x HWCPPR:%#x"
-			   " MFRR:%#x PEND:%#x h_xirr: R=%lld V=%lld\n",
-			   xc->server_num, xc->vp_id, xc->cppr, xc->hw_cppr,
-			   xc->mfrr, xc->pending,
-			   xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
+		seq_printf(m, "VCPU %d: VP:%#x/%02x\n"
+			 "    CPPR:%#x HWCPPR:%#x MFRR:%#x PEND:%#x h_xirr: R=%lld V=%lld\n",
+			 xc->server_num, xc->vp_id, xc->vp_chip_id,
+			 xc->cppr, xc->hw_cppr,
+			 xc->mfrr, xc->pending,
+			 xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
 
 		kvmppc_xive_debug_show_queues(m, vcpu);
 
@@ -2199,13 +2199,25 @@ static int xive_debug_show(struct seq_file *m, void *private)
 		t_vm_h_ipi += xc->stat_vm_h_ipi;
 	}
 
-	seq_printf(m, "Hcalls totals\n");
+	seq_puts(m, "Hcalls totals\n");
 	seq_printf(m, " H_XIRR  R=%10lld V=%10lld\n", t_rm_h_xirr, t_vm_h_xirr);
 	seq_printf(m, " H_IPOLL R=%10lld V=%10lld\n", t_rm_h_ipoll, t_vm_h_ipoll);
 	seq_printf(m, " H_CPPR  R=%10lld V=%10lld\n", t_rm_h_cppr, t_vm_h_cppr);
 	seq_printf(m, " H_EOI   R=%10lld V=%10lld\n", t_rm_h_eoi, t_vm_h_eoi);
 	seq_printf(m, " H_IPI   R=%10lld V=%10lld\n", t_rm_h_ipi, t_vm_h_ipi);
 
+	seq_puts(m, "=========\nSources\n=========\n");
+
+	for (i = 0; i <= xive->max_sbid; i++) {
+		struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+
+		if (sb) {
+			arch_spin_lock(&sb->lock);
+			kvmppc_xive_debug_show_sources(m, sb);
+			arch_spin_unlock(&sb->lock);
+		}
+	}
+
 	return 0;
 }