[PATCH v2 1/2] irqchip/gic-v3-its: Share ITS tables with a non-trusted hypervisor

From: Steven Price
Date: Wed Oct 02 2024 - 10:23:39 EST

Within a realm guest the ITS is emulated by the host. This means the
allocations must have been made available to the host by a call to
set_memory_decrypted(). Introduce an allocation function which performs
this extra call.

For the ITT use a custom genpool-based allocator that calls
set_memory_decrypted() for each page allocated, but then suballocates
the size needed for each ITT. Note that there is no mechanism
implemented to return pages from the genpool, but it is unlikely the
peak number of devices will so much larger than the normal level - so
this isn't expected to be an issue.

Co-developed-by: Suzuki K Poulose <suzuki.poulose@xxxxxxx>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@xxxxxxx>
Tested-by: Will Deacon <will@xxxxxxxxxx>
Reviewed-by: Marc Zyngier <maz@xxxxxxxxxx>
Signed-off-by: Steven Price <steven.price@xxxxxxx>
---
Changes since v1:
* Drop WARN_ONs and add a comment explaining that, if they fail,
set_memory_{en,de}crypted() will already have WARNed and that we are
purposefully leaking memory in those cases.
---
drivers/irqchip/irq-gic-v3-its.c | 151 ++++++++++++++++++++++++++-----
1 file changed, 128 insertions(+), 23 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index fdec478ba5e7..7a62fd3a8673 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -12,12 +12,14 @@
#include <linux/crash_dump.h>
#include <linux/delay.h>
#include <linux/efi.h>
+#include <linux/genalloc.h>
#include <linux/interrupt.h>
#include <linux/iommu.h>
#include <linux/iopoll.h>
#include <linux/irqdomain.h>
#include <linux/list.h>
#include <linux/log2.h>
+#include <linux/mem_encrypt.h>
#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/msi.h>
@@ -27,6 +29,7 @@
#include <linux/of_pci.h>
#include <linux/of_platform.h>
#include <linux/percpu.h>
+#include <linux/set_memory.h>
#include <linux/slab.h>
#include <linux/syscore_ops.h>

@@ -164,6 +167,7 @@ struct its_device {
struct its_node *its;
struct event_lpi_map event_map;
void *itt;
+ u32 itt_sz;
u32 nr_ites;
u32 device_id;
bool shared;
@@ -199,6 +203,93 @@ static DEFINE_IDA(its_vpeid_ida);
#define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base)
#define gic_data_rdist_vlpi_base() (gic_data_rdist_rd_base() + SZ_128K)

+static struct page *its_alloc_pages_node(int node, gfp_t gfp,
+ unsigned int order)
+{
+ struct page *page;
+ int ret = 0;
+
+ page = alloc_pages_node(node, gfp, order);
+
+ if (!page)
+ return NULL;
+
+ ret = set_memory_decrypted((unsigned long)page_address(page),
+ 1 << order);
+ /*
+ * If set_memory_decrypted() fails then we don't know what state the
+ * page is in, so we can't free it. Instead we leak it.
+ * set_memory_decrypted() will already have WARNed.
+ */
+ if (ret)
+ return NULL;
+
+ return page;
+}
+
+static struct page *its_alloc_pages(gfp_t gfp, unsigned int order)
+{
+ return its_alloc_pages_node(NUMA_NO_NODE, gfp, order);
+}
+
+static void its_free_pages(void *addr, unsigned int order)
+{
+ /*
+ * If the memory cannot be encrypted again then we must leak the pages.
+ * set_memory_encrypted will already have WARNed.
+ */
+ if (set_memory_encrypted((unsigned long)addr, 1 << order))
+ return;
+ free_pages((unsigned long)addr, order);
+}
+
+static struct gen_pool *itt_pool;
+
+static void *itt_alloc_pool(int node, int size)
+{
+ unsigned long addr;
+ struct page *page;
+
+ if (size >= PAGE_SIZE) {
+ page = its_alloc_pages_node(node,
+ GFP_KERNEL | __GFP_ZERO,
+ get_order(size));
+
+ if (!page)
+ return NULL;
+
+ return page_address(page);
+ }
+
+ do {
+ addr = gen_pool_alloc(itt_pool, size);
+ if (addr)
+ break;
+
+ page = its_alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 1);
+ if (!page)
+ break;
+
+ gen_pool_add(itt_pool, (unsigned long)page_address(page),
+ PAGE_SIZE, node);
+ } while (!addr);
+
+ return (void *)addr;
+}
+
+static void itt_free_pool(void *addr, int size)
+{
+ if (!addr)
+ return;
+
+ if (size >= PAGE_SIZE) {
+ its_free_pages(addr, get_order(size));
+ return;
+ }
+
+ gen_pool_free(itt_pool, (unsigned long)addr, size);
+}
+
/*
* Skip ITSs that have no vLPIs mapped, unless we're on GICv4.1, as we
* always have vSGIs mapped.
@@ -2181,7 +2272,8 @@ static struct page *its_allocate_prop_table(gfp_t gfp_flags)
{
struct page *prop_page;

- prop_page = alloc_pages(gfp_flags, get_order(LPI_PROPBASE_SZ));
+ prop_page = its_alloc_pages(gfp_flags,
+ get_order(LPI_PROPBASE_SZ));
if (!prop_page)
return NULL;

@@ -2192,8 +2284,8 @@ static struct page *its_allocate_prop_table(gfp_t gfp_flags)

static void its_free_prop_table(struct page *prop_page)
{
- free_pages((unsigned long)page_address(prop_page),
- get_order(LPI_PROPBASE_SZ));
+ its_free_pages(page_address(prop_page),
+ get_order(LPI_PROPBASE_SZ));
}

static bool gic_check_reserved_range(phys_addr_t addr, unsigned long size)
@@ -2315,7 +2407,8 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
order = get_order(GITS_BASER_PAGES_MAX * psz);
}

- page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO, order);
+ page = its_alloc_pages_node(its->numa_node,
+ GFP_KERNEL | __GFP_ZERO, order);
if (!page)
return -ENOMEM;

@@ -2328,7 +2421,7 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
/* 52bit PA is supported only when PageSize=64K */
if (psz != SZ_64K) {
pr_err("ITS: no 52bit PA support when psz=%d\n", psz);
- free_pages((unsigned long)base, order);
+ its_free_pages(base, order);
return -ENXIO;
}

@@ -2384,7 +2477,7 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
pr_err("ITS@%pa: %s doesn't stick: %llx %llx\n",
&its->phys_base, its_base_type_string[type],
val, tmp);
- free_pages((unsigned long)base, order);
+ its_free_pages(base, order);
return -ENXIO;
}

@@ -2523,8 +2616,8 @@ static void its_free_tables(struct its_node *its)

for (i = 0; i < GITS_BASER_NR_REGS; i++) {
if (its->tables[i].base) {
- free_pages((unsigned long)its->tables[i].base,
- its->tables[i].order);
+ its_free_pages(its->tables[i].base,
+ its->tables[i].order);
its->tables[i].base = NULL;
}
}
@@ -2790,7 +2883,8 @@ static bool allocate_vpe_l2_table(int cpu, u32 id)

/* Allocate memory for 2nd level table */
if (!table[idx]) {
- page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(psz));
+ page = its_alloc_pages(GFP_KERNEL | __GFP_ZERO,
+ get_order(psz));
if (!page)
return false;

@@ -2909,7 +3003,8 @@ static int allocate_vpe_l1_table(void)

pr_debug("np = %d, npg = %lld, psz = %d, epp = %d, esz = %d\n",
np, npg, psz, epp, esz);
- page = alloc_pages(GFP_ATOMIC | __GFP_ZERO, get_order(np * PAGE_SIZE));
+ page = its_alloc_pages(GFP_ATOMIC | __GFP_ZERO,
+ get_order(np * PAGE_SIZE));
if (!page)
return -ENOMEM;

@@ -2955,8 +3050,8 @@ static struct page *its_allocate_pending_table(gfp_t gfp_flags)
{
struct page *pend_page;

- pend_page = alloc_pages(gfp_flags | __GFP_ZERO,
- get_order(LPI_PENDBASE_SZ));
+ pend_page = its_alloc_pages(gfp_flags | __GFP_ZERO,
+ get_order(LPI_PENDBASE_SZ));
if (!pend_page)
return NULL;

@@ -2968,7 +3063,7 @@ static struct page *its_allocate_pending_table(gfp_t gfp_flags)

static void its_free_pending_table(struct page *pt)
{
- free_pages((unsigned long)page_address(pt), get_order(LPI_PENDBASE_SZ));
+ its_free_pages(page_address(pt), get_order(LPI_PENDBASE_SZ));
}

/*
@@ -3303,8 +3398,9 @@ static bool its_alloc_table_entry(struct its_node *its,

/* Allocate memory for 2nd level table */
if (!table[idx]) {
- page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
- get_order(baser->psz));
+ page = its_alloc_pages_node(its->numa_node,
+ GFP_KERNEL | __GFP_ZERO,
+ get_order(baser->psz));
if (!page)
return false;

@@ -3399,7 +3495,6 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
if (WARN_ON(!is_power_of_2(nvecs)))
nvecs = roundup_pow_of_two(nvecs);

- dev = kzalloc(sizeof(*dev), GFP_KERNEL);
/*
* Even if the device wants a single LPI, the ITT must be
* sized as a power of two (and you need at least one bit...).
@@ -3407,7 +3502,11 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
nr_ites = max(2, nvecs);
sz = nr_ites * (FIELD_GET(GITS_TYPER_ITT_ENTRY_SIZE, its->typer) + 1);
sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
- itt = kzalloc_node(sz, GFP_KERNEL, its->numa_node);
+
+ itt = itt_alloc_pool(its->numa_node, sz);
+
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+
if (alloc_lpis) {
lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
if (lpi_map)
@@ -3419,9 +3518,9 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
lpi_base = 0;
}

- if (!dev || !itt || !col_map || (!lpi_map && alloc_lpis)) {
+ if (!dev || !itt || !col_map || (!lpi_map && alloc_lpis)) {
kfree(dev);
- kfree(itt);
+ itt_free_pool(itt, sz);
bitmap_free(lpi_map);
kfree(col_map);
return NULL;
@@ -3431,6 +3530,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,

dev->its = its;
dev->itt = itt;
+ dev->itt_sz = sz;
dev->nr_ites = nr_ites;
dev->event_map.lpi_map = lpi_map;
dev->event_map.col_map = col_map;
@@ -3458,7 +3558,7 @@ static void its_free_device(struct its_device *its_dev)
list_del(&its_dev->entry);
raw_spin_unlock_irqrestore(&its_dev->its->lock, flags);
kfree(its_dev->event_map.col_map);
- kfree(its_dev->itt);
+ itt_free_pool(its_dev->itt, its_dev->itt_sz);
kfree(its_dev);
}

@@ -5116,8 +5216,9 @@ static int __init its_probe_one(struct its_node *its)
}
}

- page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
- get_order(ITS_CMD_QUEUE_SZ));
+ page = its_alloc_pages_node(its->numa_node,
+ GFP_KERNEL | __GFP_ZERO,
+ get_order(ITS_CMD_QUEUE_SZ));
if (!page) {
err = -ENOMEM;
goto out_unmap_sgir;
@@ -5181,7 +5282,7 @@ static int __init its_probe_one(struct its_node *its)
out_free_tables:
its_free_tables(its);
out_free_cmd:
- free_pages((unsigned long)its->cmd_base, get_order(ITS_CMD_QUEUE_SZ));
+ its_free_pages(its->cmd_base, get_order(ITS_CMD_QUEUE_SZ));
out_unmap_sgir:
if (its->sgir_base)
iounmap(its->sgir_base);
@@ -5667,6 +5768,10 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
bool has_v4_1 = false;
int err;

+ itt_pool = gen_pool_create(get_order(ITS_ITT_ALIGN), -1);
+ if (!itt_pool)
+ return -ENOMEM;
+
gic_rdists = rdists;

lpi_prop_prio = irq_prio;
--
2.34.1