Merge tag 'powerpc-6.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Remove support for 40x CPUs & platforms

 - Add support to the 64-bit BPF JIT for cpu v4 instructions

 - Fix PCI hotplug driver crash on powernv

 - Fix doorbell emulation for KVM on PAPR guests (nestedv2)

 - Fix KVM nested guest handling of some less used SPRs

 - Online NUMA nodes with no CPU/memory if they have a PCI device
   attached

 - Reduce memory overhead of enabling kfence on 64-bit Radix MMU kernels

 - Reimplement the iommu table_group_ops for pseries for VFIO SPAPR TCE

Thanks to: Anjali K, Artem Savkov, Athira Rajeev, Breno Leitao, Brian
King, Celeste Liu, Christophe Leroy, Esben Haabendal, Gaurav Batra,
Gautam Menghani, Haren Myneni, Hari Bathini, Jeff Johnson, Krishna
Kumar, Krzysztof Kozlowski, Nathan Lynch, Nicholas Piggin, Nick Bowler,
Nilay Shroff, Rob Herring (Arm), Shawn Anastasio, Shivaprasad G Bhat,
Sourabh Jain, Srikar Dronamraju, Timothy Pearson, Uwe Kleine-König, and
Vaibhav Jain.

* tag 'powerpc-6.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (57 commits)
  Documentation/powerpc: Mention 40x is removed
  powerpc: Remove 40x leftovers
  macintosh/therm_windtunnel: fix module unload.
  powerpc: Check only single values are passed to CPU/MMU feature checks
  powerpc/xmon: Fix disassembly CPU feature checks
  powerpc: Drop clang workaround for builtin constant checks
  powerpc64/bpf: jit support for signed division and modulo
  powerpc64/bpf: jit support for sign extended mov
  powerpc64/bpf: jit support for sign extended load
  powerpc64/bpf: jit support for unconditional byte swap
  powerpc64/bpf: jit support for 32bit offset jmp instruction
  powerpc/pci: Hotplug driver bridge support
  pci/hotplug/pnv_php: Fix hotplug driver crash on Powernv
  powerpc/configs: Update defconfig with now user-visible CONFIG_FSL_IFC
  powerpc: add missing MODULE_DESCRIPTION() macros
  macintosh/mac_hid: add MODULE_DESCRIPTION()
  KVM: PPC: add missing MODULE_DESCRIPTION() macros
  powerpc/kexec: Use of_property_read_reg()
  powerpc/64s/radix/kfence: map __kfence_pool at page granularity
  powerpc/pseries/iommu: Define spapr_tce_table_group_ops only with CONFIG_IOMMU_API
  ...

1 files changed, 21 insertions, 149 deletions

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index b70b4f93561f..76381e14e800 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -643,7 +643,7 @@ void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 		tbl->it_ops->flush(tbl);
 }
 
-static void iommu_table_clear(struct iommu_table *tbl)
+void iommu_table_clear(struct iommu_table *tbl)
 {
 	/*
 	 * In case of firmware assisted dump system goes through clean
@@ -684,7 +684,7 @@ static void iommu_table_clear(struct iommu_table *tbl)
 #endif
 }
 
-static void iommu_table_reserve_pages(struct iommu_table *tbl,
+void iommu_table_reserve_pages(struct iommu_table *tbl,
 		unsigned long res_start, unsigned long res_end)
 {
 	int i;
@@ -988,6 +988,23 @@ unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir)
 EXPORT_SYMBOL_GPL(iommu_direction_to_tce_perm);
 
 #ifdef CONFIG_IOMMU_API
+
+int dev_has_iommu_table(struct device *dev, void *data)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_dev **ppdev = data;
+
+	if (!dev)
+		return 0;
+
+	if (device_iommu_mapped(dev)) {
+		*ppdev = pdev;
+		return 1;
+	}
+
+	return 0;
+}
+
 /*
  * SPAPR TCE API
  */
@@ -1102,59 +1119,6 @@ void iommu_tce_kill(struct iommu_table *tbl,
 }
 EXPORT_SYMBOL_GPL(iommu_tce_kill);
 
-#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
-static int iommu_take_ownership(struct iommu_table *tbl)
-{
-	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
-	int ret = 0;
-
-	/*
-	 * VFIO does not control TCE entries allocation and the guest
-	 * can write new TCEs on top of existing ones so iommu_tce_build()
-	 * must be able to release old pages. This functionality
-	 * requires exchange() callback defined so if it is not
-	 * implemented, we disallow taking ownership over the table.
-	 */
-	if (!tbl->it_ops->xchg_no_kill)
-		return -EINVAL;
-
-	spin_lock_irqsave(&tbl->large_pool.lock, flags);
-	for (i = 0; i < tbl->nr_pools; i++)
-		spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
-
-	if (iommu_table_in_use(tbl)) {
-		pr_err("iommu_tce: it_map is not empty");
-		ret = -EBUSY;
-	} else {
-		memset(tbl->it_map, 0xff, sz);
-	}
-
-	for (i = 0; i < tbl->nr_pools; i++)
-		spin_unlock(&tbl->pools[i].lock);
-	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
-
-	return ret;
-}
-
-static void iommu_release_ownership(struct iommu_table *tbl)
-{
-	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
-
-	spin_lock_irqsave(&tbl->large_pool.lock, flags);
-	for (i = 0; i < tbl->nr_pools; i++)
-		spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
-
-	memset(tbl->it_map, 0, sz);
-
-	iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
-			tbl->it_reserved_end);
-
-	for (i = 0; i < tbl->nr_pools; i++)
-		spin_unlock(&tbl->pools[i].lock);
-	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
-}
-#endif
-
 int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
 {
 	/*
@@ -1187,98 +1151,6 @@ EXPORT_SYMBOL_GPL(iommu_add_device);
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*
- * A simple iommu_table_group_ops which only allows reusing the existing
- * iommu_table. This handles VFIO for POWER7 or the nested KVM.
- * The ops does not allow creating windows and only allows reusing the existing
- * one if it matches table_group->tce32_start/tce32_size/page_shift.
- */
-static unsigned long spapr_tce_get_table_size(__u32 page_shift,
-					      __u64 window_size, __u32 levels)
-{
-	unsigned long size;
-
-	if (levels > 1)
-		return ~0U;
-	size = window_size >> (page_shift - 3);
-	return size;
-}
-
-static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
-				   __u32 page_shift, __u64 window_size, __u32 levels,
-				   struct iommu_table **ptbl)
-{
-	struct iommu_table *tbl = table_group->tables[0];
-
-	if (num > 0)
-		return -EPERM;
-
-	if (tbl->it_page_shift != page_shift ||
-	    tbl->it_size != (window_size >> page_shift) ||
-	    tbl->it_indirect_levels != levels - 1)
-		return -EINVAL;
-
-	*ptbl = iommu_tce_table_get(tbl);
-	return 0;
-}
-
-static long spapr_tce_set_window(struct iommu_table_group *table_group,
-				 int num, struct iommu_table *tbl)
-{
-	return tbl == table_group->tables[num] ? 0 : -EPERM;
-}
-
-static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num)
-{
-	return 0;
-}
-
-static long spapr_tce_take_ownership(struct iommu_table_group *table_group)
-{
-	int i, j, rc = 0;
-
-	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
-		struct iommu_table *tbl = table_group->tables[i];
-
-		if (!tbl || !tbl->it_map)
-			continue;
-
-		rc = iommu_take_ownership(tbl);
-		if (!rc)
-			continue;
-
-		for (j = 0; j < i; ++j)
-			iommu_release_ownership(table_group->tables[j]);
-		return rc;
-	}
-	return 0;
-}
-
-static void spapr_tce_release_ownership(struct iommu_table_group *table_group)
-{
-	int i;
-
-	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
-		struct iommu_table *tbl = table_group->tables[i];
-
-		if (!tbl)
-			continue;
-
-		iommu_table_clear(tbl);
-		if (tbl->it_map)
-			iommu_release_ownership(tbl);
-	}
-}
-
-struct iommu_table_group_ops spapr_tce_table_group_ops = {
-	.get_table_size = spapr_tce_get_table_size,
-	.create_table = spapr_tce_create_table,
-	.set_window = spapr_tce_set_window,
-	.unset_window = spapr_tce_unset_window,
-	.take_ownership = spapr_tce_take_ownership,
-	.release_ownership = spapr_tce_release_ownership,
-};
-
-/*
  * A simple iommu_ops to allow less cruft in generic VFIO code.
  */
 static int
@@ -1299,7 +1171,7 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
 	 * The domain being set to PLATFORM from earlier
 	 * BLOCKED. The table_group ownership has to be released.
 	 */
-	table_group->ops->release_ownership(table_group);
+	table_group->ops->release_ownership(table_group, dev);
 	iommu_group_put(grp);
 
 	return 0;
@@ -1327,7 +1199,7 @@ spapr_tce_blocked_iommu_attach_dev(struct iommu_domain *platform_domain,
 	 * also sets the dma_api ops
 	 */
 	table_group = iommu_group_get_iommudata(grp);
-	ret = table_group->ops->take_ownership(table_group);
+	ret = table_group->ops->take_ownership(table_group, dev);
 	iommu_group_put(grp);
 
 	return ret;