aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/devicetree/bindings/iommu/xen,grant-dma.yaml39
-rw-r--r--Documentation/filesystems/netfs_library.rst37
-rw-r--r--MAINTAINERS8
-rw-r--r--arch/arm/include/asm/xen/xen-ops.h2
-rw-r--r--arch/arm/mm/dma-mapping.c7
-rw-r--r--arch/arm/xen/enlighten.c2
-rw-r--r--arch/arm64/include/asm/xen/xen-ops.h2
-rw-r--r--arch/arm64/mm/dma-mapping.c7
-rw-r--r--arch/powerpc/Kconfig2
-rw-r--r--arch/powerpc/include/asm/thread_info.h10
-rw-r--r--arch/powerpc/kernel/Makefile2
-rw-r--r--arch/powerpc/kernel/process.c4
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-fpu.c20
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace.c3
-rw-r--r--arch/powerpc/kernel/rtas.c4
-rw-r--r--arch/powerpc/kexec/crash.c2
-rw-r--r--arch/powerpc/mm/nohash/kaslr_booke.c8
-rw-r--r--arch/powerpc/platforms/powernv/Makefile1
-rw-r--r--arch/powerpc/platforms/pseries/papr_scm.c3
-rw-r--r--arch/s390/Kconfig1
-rw-r--r--arch/s390/mm/init.c13
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/mm/mem_encrypt.c7
-rw-r--r--arch/x86/mm/mem_encrypt_amd.c4
-rw-r--r--arch/x86/xen/enlighten_hvm.c2
-rw-r--r--arch/x86/xen/enlighten_pv.c2
-rw-r--r--drivers/platform/mips/Kconfig2
-rw-r--r--drivers/virtio/Kconfig6
-rw-r--r--drivers/virtio/virtio.c5
-rw-r--r--drivers/xen/Kconfig20
-rw-r--r--drivers/xen/Makefile2
-rw-r--r--drivers/xen/grant-dma-iommu.c78
-rw-r--r--drivers/xen/grant-dma-ops.c346
-rw-r--r--drivers/xen/grant-table.c251
-rw-r--r--drivers/xen/xlate_mmu.c1
-rw-r--r--fs/9p/cache.c4
-rw-r--r--fs/9p/v9fs.c2
-rw-r--r--fs/9p/v9fs.h10
-rw-r--r--fs/9p/vfs_addr.c2
-rw-r--r--fs/9p/vfs_inode.c4
-rw-r--r--fs/afs/callback.c2
-rw-r--r--fs/afs/dir.c32
-rw-r--r--fs/afs/dir_edit.c10
-rw-r--r--fs/afs/dir_silly.c4
-rw-r--r--fs/afs/dynroot.c2
-rw-r--r--fs/afs/file.c4
-rw-r--r--fs/afs/fs_operation.c6
-rw-r--r--fs/afs/inode.c41
-rw-r--r--fs/afs/internal.h23
-rw-r--r--fs/afs/super.c6
-rw-r--r--fs/afs/write.c21
-rw-r--r--fs/ceph/addr.c4
-rw-r--r--fs/ceph/cache.c4
-rw-r--r--fs/ceph/cache.h2
-rw-r--r--fs/ceph/caps.c104
-rw-r--r--fs/ceph/file.c2
-rw-r--r--fs/ceph/inode.c13
-rw-r--r--fs/ceph/mds_client.c4
-rw-r--r--fs/ceph/snap.c8
-rw-r--r--fs/ceph/super.c2
-rw-r--r--fs/ceph/super.h10
-rw-r--r--fs/ceph/xattr.c14
-rw-r--r--fs/cifs/cifsfs.c8
-rw-r--r--fs/cifs/cifsglob.h12
-rw-r--r--fs/cifs/file.c8
-rw-r--r--fs/cifs/fscache.c8
-rw-r--r--fs/cifs/fscache.h8
-rw-r--r--fs/cifs/inode.c4
-rw-r--r--fs/cifs/misc.c4
-rw-r--r--fs/cifs/smb2ops.c8
-rw-r--r--fs/ext2/inode.c2
-rw-r--r--fs/fs-writeback.c37
-rw-r--r--fs/inode.c2
-rw-r--r--fs/netfs/buffered_read.c6
-rw-r--r--fs/netfs/internal.h2
-rw-r--r--fs/netfs/objects.c2
-rw-r--r--fs/quota/dquot.c10
-rw-r--r--include/asm-generic/Kbuild1
-rw-r--r--include/asm-generic/platform-feature.h8
-rw-r--r--include/linux/netfs.h41
-rw-r--r--include/linux/platform-feature.h19
-rw-r--r--include/linux/virtio_config.h9
-rw-r--r--include/xen/arm/xen-ops.h18
-rw-r--r--include/xen/grant_table.h4
-rw-r--r--include/xen/xen-ops.h13
-rw-r--r--include/xen/xen.h8
-rw-r--r--kernel/Makefile2
-rw-r--r--kernel/platform-feature.c27
88 files changed, 1136 insertions, 379 deletions
diff --git a/Documentation/devicetree/bindings/iommu/xen,grant-dma.yaml b/Documentation/devicetree/bindings/iommu/xen,grant-dma.yaml
new file mode 100644
index 000000000000..be1539d234f9
--- /dev/null
+++ b/Documentation/devicetree/bindings/iommu/xen,grant-dma.yaml
@@ -0,0 +1,39 @@
+# SPDX-License-Identifier: (GPL-2.0-only or BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iommu/xen,grant-dma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Xen specific IOMMU for virtualized devices (e.g. virtio)
+
+maintainers:
+ - Stefano Stabellini <[email protected]>
+
+description:
+ The Xen IOMMU represents the Xen grant table interface. Grant mappings
+ are to be used with devices connected to the Xen IOMMU using the "iommus"
+ property, which also specifies the ID of the backend domain.
+ The binding is required to restrict memory access using Xen grant mappings.
+
+properties:
+ compatible:
+ const: xen,grant-dma
+
+ '#iommu-cells':
+ const: 1
+ description:
+ The single cell is the domid (domain ID) of the domain where the backend
+ is running.
+
+required:
+ - compatible
+ - "#iommu-cells"
+
+additionalProperties: false
+
+examples:
+ - |
+ iommu {
+ compatible = "xen,grant-dma";
+ #iommu-cells = <1>;
+ };
diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index a80a59941d2f..3276c3d55142 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -37,30 +37,31 @@ The network filesystem helper library needs a place to store a bit of state for
its use on each netfs inode it is helping to manage. To this end, a context
structure is defined::
- struct netfs_i_context {
+ struct netfs_inode {
+ struct inode inode;
const struct netfs_request_ops *ops;
- struct fscache_cookie *cache;
+ struct fscache_cookie *cache;
};
-A network filesystem that wants to use netfs lib must place one of these
-directly after the VFS ``struct inode`` it allocates, usually as part of its
-own struct. This can be done in a way similar to the following::
+A network filesystem that wants to use netfs lib must place one of these in its
+inode wrapper struct instead of the VFS ``struct inode``. This can be done in
+a way similar to the following::
struct my_inode {
- struct {
- /* These must be contiguous */
- struct inode vfs_inode;
- struct netfs_i_context netfs_ctx;
- };
+ struct netfs_inode netfs; /* Netfslib context and vfs inode */
...
};
-This allows netfslib to find its state by simple offset from the inode pointer,
-thereby allowing the netfslib helper functions to be pointed to directly by the
-VFS/VM operation tables.
+This allows netfslib to find its state by using ``container_of()`` from the
+inode pointer, thereby allowing the netfslib helper functions to be pointed to
+directly by the VFS/VM operation tables.
The structure contains the following fields:
+ * ``inode``
+
+ The VFS inode structure.
+
* ``ops``
The set of operations provided by the network filesystem to netfslib.
@@ -78,14 +79,12 @@ To help deal with the per-inode context, a number helper functions are
provided. Firstly, a function to perform basic initialisation on a context and
set the operations table pointer::
- void netfs_i_context_init(struct inode *inode,
- const struct netfs_request_ops *ops);
+ void netfs_inode_init(struct inode *inode,
+ const struct netfs_request_ops *ops);
-then two functions to cast between the VFS inode structure and the netfs
-context::
+then a function to cast from the VFS inode structure to the netfs context::
- struct netfs_i_context *netfs_i_context(struct inode *inode);
- struct inode *netfs_inode(struct netfs_i_context *ctx);
+ struct netfs_inode *netfs_node(struct inode *inode);
and finally, a function to get the cache cookie pointer from the context
attached to an inode (or NULL if fscache is disabled)::
diff --git a/MAINTAINERS b/MAINTAINERS
index 39e78f58b0aa..de8350706c5d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15830,6 +15830,14 @@ S: Maintained
F: Documentation/devicetree/bindings/iio/chemical/plantower,pms7003.yaml
F: drivers/iio/chemical/pms7003.c
+PLATFORM FEATURE INFRASTRUCTURE
+M: Juergen Gross <[email protected]>
+S: Maintained
+F: arch/*/include/asm/platform-feature.h
+F: include/asm-generic/platform-feature.h
+F: include/linux/platform-feature.h
+F: kernel/platform-feature.c
+
PLDMFW LIBRARY
M: Jacob Keller <[email protected]>
S: Maintained
diff --git a/arch/arm/include/asm/xen/xen-ops.h b/arch/arm/include/asm/xen/xen-ops.h
new file mode 100644
index 000000000000..7ebb7eb0bd93
--- /dev/null
+++ b/arch/arm/include/asm/xen/xen-ops.h
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <xen/arm/xen-ops.h>
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 82ffac621854..059cce018570 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -33,7 +33,7 @@
#include <asm/dma-iommu.h>
#include <asm/mach/map.h>
#include <asm/system_info.h>
-#include <xen/swiotlb-xen.h>
+#include <asm/xen/xen-ops.h>
#include "dma.h"
#include "mm.h"
@@ -2287,10 +2287,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
set_dma_ops(dev, dma_ops);
-#ifdef CONFIG_XEN
- if (xen_initial_domain())
- dev->dma_ops = &xen_swiotlb_dma_ops;
-#endif
+ xen_setup_dma_ops(dev);
dev->archdata.dma_ops_setup = true;
}
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 07eb69f9e7df..1f9c3ba32833 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -443,6 +443,8 @@ static int __init xen_guest_init(void)
if (!xen_domain())
return 0;
+ xen_set_restricted_virtio_memory_access();
+
if (!acpi_disabled)
xen_acpi_guest_init();
else
diff --git a/arch/arm64/include/asm/xen/xen-ops.h b/arch/arm64/include/asm/xen/xen-ops.h
new file mode 100644
index 000000000000..7ebb7eb0bd93
--- /dev/null
+++ b/arch/arm64/include/asm/xen/xen-ops.h
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <xen/arm/xen-ops.h>
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 6719f9efea09..6099c81b9322 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -9,9 +9,9 @@
#include <linux/dma-map-ops.h>
#include <linux/dma-iommu.h>
#include <xen/xen.h>
-#include <xen/swiotlb-xen.h>
#include <asm/cacheflush.h>
+#include <asm/xen/xen-ops.h>
void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
enum dma_data_direction dir)
@@ -52,8 +52,5 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
if (iommu)
iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1);
-#ifdef CONFIG_XEN
- if (xen_swiotlb_detect())
- dev->dma_ops = &xen_swiotlb_dma_ops;
-#endif
+ xen_setup_dma_ops(dev);
}
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index be68c1f02b79..c2ce2e60c8f0 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -223,7 +223,6 @@ config PPC
select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
select HAVE_IOREMAP_PROT
- select HAVE_IRQ_EXIT_ON_IRQ_STACK
select HAVE_IRQ_TIME_ACCOUNTING
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZMA if DEFAULT_UIMAGE
@@ -786,7 +785,6 @@ config THREAD_SHIFT
range 13 15
default "15" if PPC_256K_PAGES
default "14" if PPC64
- default "14" if KASAN
default "13"
help
Used to define the stack size. The default is almost always what you
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 125328d1b980..af58f1ed3952 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -14,10 +14,16 @@
#ifdef __KERNEL__
-#if defined(CONFIG_VMAP_STACK) && CONFIG_THREAD_SHIFT < PAGE_SHIFT
+#ifdef CONFIG_KASAN
+#define MIN_THREAD_SHIFT (CONFIG_THREAD_SHIFT + 1)
+#else
+#define MIN_THREAD_SHIFT CONFIG_THREAD_SHIFT
+#endif
+
+#if defined(CONFIG_VMAP_STACK) && MIN_THREAD_SHIFT < PAGE_SHIFT
#define THREAD_SHIFT PAGE_SHIFT
#else
-#define THREAD_SHIFT CONFIG_THREAD_SHIFT
+#define THREAD_SHIFT MIN_THREAD_SHIFT
#endif
#define THREAD_SIZE (1 << THREAD_SHIFT)
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 2e2a2a9bcf43..f91f0f29a566 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -37,6 +37,8 @@ KASAN_SANITIZE_paca.o := n
KASAN_SANITIZE_setup_64.o := n
KASAN_SANITIZE_mce.o := n
KASAN_SANITIZE_mce_power.o := n
+KASAN_SANITIZE_udbg.o := n
+KASAN_SANITIZE_udbg_16550.o := n
# we have to be particularly careful in ppc64 to exclude code that
# runs with translations off, as we cannot access the shadow with
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index b62046bf3bb8..ee0433809621 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -2158,12 +2158,12 @@ static unsigned long ___get_wchan(struct task_struct *p)
return 0;
do {
- sp = *(unsigned long *)sp;
+ sp = READ_ONCE_NOCHECK(*(unsigned long *)sp);
if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD) ||
task_is_running(p))
return 0;
if (count > 0) {
- ip = ((unsigned long *)sp)[STACK_FRAME_LR_SAVE];
+ ip = READ_ONCE_NOCHECK(((unsigned long *)sp)[STACK_FRAME_LR_SAVE]);
if (!in_sched_functions(ip))
return ip;
}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-fpu.c b/arch/powerpc/kernel/ptrace/ptrace-fpu.c
index 5dca19361316..09c49632bfe5 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-fpu.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-fpu.c
@@ -17,9 +17,13 @@ int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data)
#ifdef CONFIG_PPC_FPU_REGS
flush_fp_to_thread(child);
- if (fpidx < (PT_FPSCR - PT_FPR0))
- memcpy(data, &child->thread.TS_FPR(fpidx), sizeof(long));
- else
+ if (fpidx < (PT_FPSCR - PT_FPR0)) {
+ if (IS_ENABLED(CONFIG_PPC32))
+ // On 32-bit the index we are passed refers to 32-bit words
+ *data = ((u32 *)child->thread.fp_state.fpr)[fpidx];
+ else
+ memcpy(data, &child->thread.TS_FPR(fpidx), sizeof(long));
+ } else
*data = child->thread.fp_state.fpscr;
#else
*data = 0;
@@ -39,9 +43,13 @@ int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data)
#ifdef CONFIG_PPC_FPU_REGS
flush_fp_to_thread(child);
- if (fpidx < (PT_FPSCR - PT_FPR0))
- memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long));
- else
+ if (fpidx < (PT_FPSCR - PT_FPR0)) {
+ if (IS_ENABLED(CONFIG_PPC32))
+ // On 32-bit the index we are passed refers to 32-bit words
+ ((u32 *)child->thread.fp_state.fpr)[fpidx] = data;
+ else
+ memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long));
+ } else
child->thread.fp_state.fpscr = data;
#endif
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 4d2dc22d4a2d..5d7a72b41ae7 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -444,4 +444,7 @@ void __init pt_regs_check(void)
* real registers.
*/
BUILD_BUG_ON(PT_DSCR < sizeof(struct user_pt_regs) / sizeof(unsigned long));
+
+ // ptrace_get/put_fpr() rely on PPC32 and VSX being incompatible
+ BUILD_BUG_ON(IS_ENABLED(CONFIG_PPC32) && IS_ENABLED(CONFIG_VSX));
}
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 9bb43aa53d43..a6fce3106e02 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -993,8 +993,8 @@ int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...)
*
* Return: A pointer to the specified errorlog or NULL if not found.
*/
-struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
- uint16_t section_id)
+noinstr struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
+ uint16_t section_id)
{
struct rtas_ext_event_log_v6 *ext_log =
(struct rtas_ext_event_log_v6 *)log->buffer;
diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c
index d85fa9fc6f3c..80f54723cf6d 100644
--- a/arch/powerpc/kexec/crash.c
+++ b/arch/powerpc/kexec/crash.c
@@ -224,7 +224,7 @@ void crash_kexec_secondary(struct pt_regs *regs)
/* wait for all the CPUs to hit real mode but timeout if they don't come in */
#if defined(CONFIG_SMP) && defined(CONFIG_PPC64)
-static void __maybe_unused crash_kexec_wait_realmode(int cpu)
+noinstr static void __maybe_unused crash_kexec_wait_realmode(int cpu)
{
unsigned int msecs;
int i;
diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c
index 1f3f9fedf1bc..0d04f9d5da8d 100644
--- a/arch/powerpc/mm/nohash/kaslr_booke.c
+++ b/arch/powerpc/mm/nohash/kaslr_booke.c
@@ -19,7 +19,6 @@
#include <asm/cacheflush.h>
#include <asm/kdump.h>
#include <mm/mmu_decl.h>
-#include <generated/compile.h>
#include <generated/utsrelease.h>
struct regions {
@@ -37,10 +36,6 @@ struct regions {
int reserved_mem_size_cells;
};
-/* Simplified build-specific string for starting entropy. */
-static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
- LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
-
struct regions __initdata regions;
static __init void kaslr_get_cmdline(void *fdt)
@@ -71,7 +66,8 @@ static unsigned long __init get_boot_seed(void *fdt)
{
unsigned long hash = 0;
- hash = rotate_xor(hash, build_str, sizeof(build_str));
+ /* build-specific string for starting entropy. */
+ hash = rotate_xor(hash, linux_banner, strlen(linux_banner));
hash = rotate_xor(hash, fdt, fdt_totalsize(fdt));
return hash;
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 6488b3842199..19f0fc5c6f1b 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -4,6 +4,7 @@
# in particular, idle code runs a bunch of things in real mode
KASAN_SANITIZE_idle.o := n
KASAN_SANITIZE_pci-ioda.o := n
+KASAN_SANITIZE_pci-ioda-tce.o := n
# pnv_machine_check_early
KASAN_SANITIZE_setup.o := n
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 181b855b3050..82cae08976bc 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -465,6 +465,9 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu
u32 available_events;
int index, rc = 0;
+ if (!p->stat_buffer_len)
+ return -ENOENT;
+
available_events = (p->stat_buffer_len - sizeof(struct papr_scm_perf_stats))
/ sizeof(struct papr_scm_perf_stat);
if (available_events == 0)
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 5126a5db41fd..91c0b80a8bf0 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -769,7 +769,6 @@ menu "Virtualization"
config PROTECTED_VIRTUALIZATION_GUEST
def_bool n
prompt "Protected virtualization guest support"
- select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
help
Select this option, if you want to be able to run this
kernel as a protected virtualization KVM guest.
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 6fb6bf64326f..6a0ac00d5a42 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -31,6 +31,7 @@
#include <linux/cma.h>
#include <linux/gfp.h>
#include <linux/dma-direct.h>
+#include <linux/platform-feature.h>
#include <asm/processor.h>
#include <linux/uaccess.h>
#include <asm/pgalloc.h>
@@ -168,22 +169,14 @@ bool force_dma_unencrypted(struct device *dev)
return is_prot_virt_guest();
}
-#ifdef CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
-
-int arch_has_restricted_virtio_memory_access(void)
-{
- return is_prot_virt_guest();
-}
-EXPORT_SYMBOL(arch_has_restricted_virtio_memory_access);
-
-#endif
-
/* protected virtualization */
static void pv_init(void)
{
if (!is_prot_virt_guest())
return;
+ platform_set(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS);
+
/* make sure bounce buffers are shared */
swiotlb_init(true, SWIOTLB_FORCE | SWIOTLB_VERBOSE);
swiotlb_update_mem_attributes();
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9783ebc4e021..be0b95e51df6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1542,7 +1542,6 @@ config X86_CPA_STATISTICS
config X86_MEM_ENCRYPT
select ARCH_HAS_FORCE_DMA_UNENCRYPTED
select DYNAMIC_PHYSICAL_MASK
- select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
def_bool n
config AMD_MEM_ENCRYPT
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 11350e2fd736..9f27e14e185f 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -12,7 +12,6 @@
#include <linux/swiotlb.h>
#include <linux/cc_platform.h>
#include <linux/mem_encrypt.h>
-#include <linux/virtio_config.h>
/* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */
bool force_dma_unencrypted(struct device *dev)
@@ -87,9 +86,3 @@ void __init mem_encrypt_init(void)
print_mem_encrypt_feature_info();
}
-
-int arch_has_restricted_virtio_memory_access(void)
-{
- return cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT);
-}
-EXPORT_SYMBOL_GPL(arch_has_restricted_virtio_memory_access);
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index e8f7953fda83..f6d038e2cd8e 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -21,6 +21,7 @@
#include <linux/dma-mapping.h>
#include <linux/virtio_config.h>
#include <linux/cc_platform.h>
+#include <linux/platform-feature.h>
#include <asm/tlbflush.h>
#include <asm/fixmap.h>
@@ -242,6 +243,9 @@ void __init sev_setup_arch(void)
size = total_mem * 6 / 100;
size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G);
swiotlb_adjust_size(size);
+
+ /* Set restricted memory access for virtio. */
+ platform_set(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS);
}
static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 517a9d8d8f94..8b71b1dd7639 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -195,6 +195,8 @@ static void __init xen_hvm_guest_init(void)
if (xen_pv_domain())
return;
+ xen_set_restricted_virtio_memory_access();
+
init_hvm_pv_info();
reserve_shared_info();
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index f33a4421e7cd..e3297b15701c 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -109,6 +109,8 @@ static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);
static void __init xen_pv_init_platform(void)
{
+ xen_set_restricted_virtio_memory_access();
+
populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP));
set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
diff --git a/drivers/platform/mips/Kconfig b/drivers/platform/mips/Kconfig
index d421e1482395..6b51ad01f791 100644
--- a/drivers/platform/mips/Kconfig
+++ b/drivers/platform/mips/Kconfig
@@ -17,7 +17,7 @@ menuconfig MIPS_PLATFORM_DEVICES
if MIPS_PLATFORM_DEVICES
config CPU_HWMON
- tristate "Loongson-3 CPU HWMon Driver"
+ bool "Loongson-3 CPU HWMon Driver"
depends on MACH_LOONGSON64
select HWMON
default y
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index b5adf6abd241..a6dc8b5846fe 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -6,12 +6,6 @@ config VIRTIO
bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_RPMSG
or CONFIG_S390_GUEST.
-config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
- bool
- help
- This option is selected if the architecture may need to enforce
- VIRTIO_F_ACCESS_PLATFORM
-
config VIRTIO_PCI_LIB
tristate
help
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index ef04a96942bf..6bace84ae37e 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -5,6 +5,7 @@
#include <linux/module.h>
#include <linux/idr.h>
#include <linux/of.h>
+#include <linux/platform-feature.h>
#include <uapi/linux/virtio_ids.h>
/* Unique numbering for virtio devices. */
@@ -170,12 +171,10 @@ EXPORT_SYMBOL_GPL(virtio_add_status);
static int virtio_features_ok(struct virtio_device *dev)
{
unsigned int status;
- int ret;
might_sleep();
- ret = arch_has_restricted_virtio_memory_access();
- if (ret) {
+ if (platform_has(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS)) {
if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1)) {
dev_warn(&dev->dev,
"device must provide VIRTIO_F_VERSION_1\n");
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 120d32f164ac..bfd5f4f706bc 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -335,4 +335,24 @@ config XEN_UNPOPULATED_ALLOC
having to balloon out RAM regions in order to obtain physical memory
space to create such mappings.
+config XEN_GRANT_DMA_IOMMU
+ bool
+ select IOMMU_API
+
+config XEN_GRANT_DMA_OPS
+ bool
+ select DMA_OPS
+
+config XEN_VIRTIO
+ bool "Xen virtio support"
+ depends on VIRTIO
+ select XEN_GRANT_DMA_OPS
+ select XEN_GRANT_DMA_IOMMU if OF
+ help
+ Enable virtio support for running as Xen guest. Depending on the
+ guest type this will require special support on the backend side
+ (qemu or kernel, depending on the virtio device types used).
+
+ If in doubt, say n.
+
endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 5aae66e638a7..c0503f1c7d5b 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -39,3 +39,5 @@ xen-gntalloc-y := gntalloc.o
xen-privcmd-y := privcmd.o privcmd-buf.o
obj-$(CONFIG_XEN_FRONT_PGDIR_SHBUF) += xen-front-pgdir-shbuf.o
obj-$(CONFIG_XEN_UNPOPULATED_ALLOC) += unpopulated-alloc.o
+obj-$(CONFIG_XEN_GRANT_DMA_OPS) += grant-dma-ops.o
+obj-$(CONFIG_XEN_GRANT_DMA_IOMMU) += grant-dma-iommu.o
diff --git a/drivers/xen/grant-dma-iommu.c b/drivers/xen/grant-dma-iommu.c
new file mode 100644
index 000000000000..16b8bc0c0b33
--- /dev/null
+++ b/drivers/xen/grant-dma-iommu.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Stub IOMMU driver which does nothing.
+ * The main purpose of it being present is to reuse generic IOMMU device tree
+ * bindings by Xen grant DMA-mapping layer.
+ *
+ * Copyright (C) 2022 EPAM Systems Inc.
+ */
+
+#include <linux/iommu.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+struct grant_dma_iommu_device {
+ struct device *dev;
+ struct iommu_device iommu;
+};
+
+/* Nothing is really needed here */
+static const struct iommu_ops grant_dma_iommu_ops;
+
+static const struct of_device_id grant_dma_iommu_of_match[] = {
+ { .compatible = "xen,grant-dma" },
+ { },
+};
+
+static int grant_dma_iommu_probe(struct platform_device *pdev)
+{
+ struct grant_dma_iommu_device *mmu;
+ int ret;
+
+ mmu = devm_kzalloc(&pdev->dev, sizeof(*mmu), GFP_KERNEL);
+ if (!mmu)
+ return -ENOMEM;
+
+ mmu->dev = &pdev->dev;
+
+ ret = iommu_device_register(&mmu->iommu, &grant_dma_iommu_ops, &pdev->dev);
+ if (ret)
+ return ret;
+
+ platform_set_drvdata(pdev, mmu);
+
+ return 0;
+}
+
+static int grant_dma_iommu_remove(struct platform_device *pdev)
+{
+ struct grant_dma_iommu_device *mmu = platform_get_drvdata(pdev);
+
+ platform_set_drvdata(pdev, NULL);
+ iommu_device_unregister(&mmu->iommu);
+
+ return 0;
+}
+
+static struct platform_driver grant_dma_iommu_driver = {
+ .driver = {
+ .name = "grant-dma-iommu",
+ .of_match_table = grant_dma_iommu_of_match,
+ },
+ .probe = grant_dma_iommu_probe,
+ .remove = grant_dma_iommu_remove,
+};
+
+static int __init grant_dma_iommu_init(void)
+{
+ struct device_node *iommu_np;
+
+ iommu_np = of_find_matching_node(NULL, grant_dma_iommu_of_match);
+ if (!iommu_np)
+ return 0;
+
+ of_node_put(iommu_np);
+
+ return platform_driver_register(&grant_dma_iommu_driver);
+}
+subsys_initcall(grant_dma_iommu_init);
diff --git a/drivers/xen/grant-dma-ops.c b/drivers/xen/grant-dma-ops.c
new file mode 100644
index 000000000000..fc0142484001
--- /dev/null
+++ b/drivers/xen/grant-dma-ops.c
@@ -0,0 +1,346 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Xen grant DMA-mapping layer - contains special DMA-mapping routines
+ * for providing grant references as DMA addresses to be used by frontends
+ * (e.g. virtio) in Xen guests
+ *
+ * Copyright (c) 2021, Juergen Gross <[email protected]>
+ */
+
+#include <linux/module.h>
+#include <linux/dma-map-ops.h>
+#include <linux/of.h>
+#include <linux/pfn.h>
+#include <linux/xarray.h>
+#include <xen/xen.h>
+#include <xen/xen-ops.h>
+#include <xen/grant_table.h>
+
+struct xen_grant_dma_data {
+ /* The ID of backend domain */
+ domid_t backend_domid;
+ /* Is device behaving sane? */
+ bool broken;
+};
+
+static DEFINE_XARRAY(xen_grant_dma_devices);
+
+#define XEN_GRANT_DMA_ADDR_OFF (1ULL << 63)
+
+static inline dma_addr_t grant_to_dma(grant_ref_t grant)
+{
+ return XEN_GRANT_DMA_ADDR_OFF | ((dma_addr_t)grant << PAGE_SHIFT);
+}
+
+static inline grant_ref_t dma_to_grant(dma_addr_t dma)
+{
+ return (grant_ref_t)((dma & ~XEN_GRANT_DMA_ADDR_OFF) >> PAGE_SHIFT);
+}
+
+static struct xen_grant_dma_data *find_xen_grant_dma_data(struct device *dev)
+{
+ struct xen_grant_dma_data *data;
+
+ xa_lock(&xen_grant_dma_devices);
+ data = xa_load(&xen_grant_dma_devices, (unsigned long)dev);
+ xa_unlock(&xen_grant_dma_devices);
+
+ return data;
+}
+
+/*
+ * DMA ops for Xen frontends (e.g. virtio).
+ *
+ * Used to act as a kind of software IOMMU for Xen guests by using grants as
+ * DMA addresses.
+ * Such a DMA address is formed by using the grant reference as a frame
+ * number and setting the highest address bit (this bit is for the backend
+ * to be able to distinguish it from e.g. a mmio address).
+ */
+static void *xen_grant_dma_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp,
+ unsigned long attrs)
+{
+ struct xen_grant_dma_data *data;
+ unsigned int i, n_pages = PFN_UP(size);
+ unsigned long pfn;
+ grant_ref_t grant;
+ void *ret;
+
+ data = find_xen_grant_dma_data(dev);
+ if (!data)
+ return NULL;
+
+ if (unlikely(data->broken))
+ return NULL;
+
+ ret = alloc_pages_exact(n_pages * PAGE_SIZE, gfp);
+ if (!ret)
+ return NULL;
+
+ pfn = virt_to_pfn(ret);
+
+ if (gnttab_alloc_grant_reference_seq(n_pages, &grant)) {
+ free_pages_exact(ret, n_pages * PAGE_SIZE);
+ return NULL;
+ }
+
+ for (i = 0; i < n_pages; i++) {
+ gnttab_grant_foreign_access_ref(grant + i, data->backend_domid,
+ pfn_to_gfn(pfn + i), 0);
+ }
+
+ *dma_handle = grant_to_dma(grant);
+
+ return ret;
+}
+
+static void xen_grant_dma_free(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_handle, unsigned long attrs)
+{
+ struct xen_grant_dma_data *data;
+ unsigned int i, n_pages = PFN_UP(size);
+ grant_ref_t grant;
+
+ data = find_xen_grant_dma_data(dev);
+ if (!data)
+ return;
+
+ if (unlikely(data->broken))
+ return;
+
+ grant = dma_to_grant(dma_handle);
+
+ for (i = 0; i < n_pages; i++) {
+ if (unlikely(!gnttab_end_foreign_access_ref(grant + i))) {
+ dev_alert(dev, "Grant still in use by backend domain, disabled for further use\n");
+ data->broken = true;
+ return;
+ }
+ }
+
+ gnttab_free_grant_reference_seq(grant, n_pages);
+
+ free_pages_exact(vaddr, n_pages * PAGE_SIZE);
+}
+
+static struct page *xen_grant_dma_alloc_pages(struct device *dev, size_t size,
+ dma_addr_t *dma_handle,
+ enum dma_data_direction dir,
+ gfp_t gfp)
+{
+ void *vaddr;
+
+ vaddr = xen_grant_dma_alloc(dev, size, dma_handle, gfp, 0);
+ if (!vaddr)
+ return NULL;
+
+ return virt_to_page(vaddr);
+}
+
+static void xen_grant_dma_free_pages(struct device *dev, size_t size,
+ struct page *vaddr, dma_addr_t dma_handle,
+ enum dma_data_direction dir)
+{
+ xen_grant_dma_free(dev, size, page_to_virt(vaddr), dma_handle, 0);
+}
+
+static dma_addr_t xen_grant_dma_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ struct xen_grant_dma_data *data;
+ unsigned int i, n_pages = PFN_UP(size);
+ grant_ref_t grant;
+ dma_addr_t dma_handle;
+
+ if (WARN_ON(dir == DMA_NONE))
+ return DMA_MAPPING_ERROR;
+
+ data = find_xen_grant_dma_data(dev);
+ if (!data)
+ return DMA_MAPPING_ERROR;
+
+ if (unlikely(data->broken))
+ return DMA_MAPPING_ERROR;
+
+ if (gnttab_alloc_grant_reference_seq(n_pages, &grant))
+ return DMA_MAPPING_ERROR;
+
+ for (i = 0; i < n_pages; i++) {
+ gnttab_grant_foreign_access_ref(grant + i, data->backend_domid,
+ xen_page_to_gfn(page) + i, dir == DMA_TO_DEVICE);
+ }
+
+ dma_handle = grant_to_dma(grant) + offset;
+
+ return dma_handle;
+}
+
+static void xen_grant_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ struct xen_grant_dma_data *data;
+ unsigned int i, n_pages = PFN_UP(size);
+ grant_ref_t grant;
+
+ if (WARN_ON(dir == DMA_NONE))
+ return;
+
+ data = find_xen_grant_dma_data(dev);
+ if (!data)
+ return;
+
+ if (unlikely(data->broken))
+ return;
+
+ grant = dma_to_grant(dma_handle);
+
+ for (i = 0; i < n_pages; i++) {
+ if (unlikely(!gnttab_end_foreign_access_ref(grant + i))) {
+ dev_alert(dev, "Grant still in use by backend domain, disabled for further use\n");
+ data->broken = true;
+ return;
+ }
+ }
+
+ gnttab_free_grant_reference_seq(grant, n_pages);
+}
+
+static void xen_grant_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+ int nents, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ struct scatterlist *s;
+ unsigned int i;
+
+ if (WARN_ON(dir == DMA_NONE))
+ return;
+
+ for_each_sg(sg, s, nents, i)
+ xen_grant_dma_unmap_page(dev, s->dma_address, sg_dma_len(s), dir,
+ attrs);
+}
+
+static int xen_grant_dma_map_sg(struct device *dev, struct scatterlist *sg,
+ int nents, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ struct scatterlist *s;
+ unsigned int i;
+
+ if (WARN_ON(dir == DMA_NONE))
+ return -EINVAL;
+
+ for_each_sg(sg, s, nents, i) {
+ s->dma_address = xen_grant_dma_map_page(dev, sg_page(s), s->offset,
+ s->length, dir, attrs);
+ if (s->dma_address == DMA_MAPPING_ERROR)
+ goto out;
+
+ sg_dma_len(s) = s->length;
+ }
+
+ return nents;
+
+out:
+ xen_grant_dma_unmap_sg(dev, sg, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
+ sg_dma_len(sg) = 0;
+
+ return -EIO;
+}
+
+static int xen_grant_dma_supported(struct device *dev, u64 mask)
+{
+ return mask == DMA_BIT_MASK(64);
+}
+
+static const struct dma_map_ops xen_grant_dma_ops = {
+ .alloc = xen_grant_dma_alloc,
+ .free = xen_grant_dma_free,
+ .alloc_pages = xen_grant_dma_alloc_pages,
+ .free_pages = xen_grant_dma_free_pages,
+ .mmap = dma_common_mmap,
+ .get_sgtable = dma_common_get_sgtable,
+ .map_page = xen_grant_dma_map_page,
+ .unmap_page = xen_grant_dma_unmap_page,
+ .map_sg = xen_grant_dma_map_sg,
+ .unmap_sg = xen_grant_dma_unmap_sg,
+ .dma_supported = xen_grant_dma_supported,
+};
+
+bool xen_is_grant_dma_device(struct device *dev)
+{
+ struct device_node *iommu_np;
+ bool has_iommu;
+
+ /* XXX Handle only DT devices for now */
+ if (!dev->of_node)
+ return false;
+
+ iommu_np = of_parse_phandle(dev->of_node, "iommus", 0);
+ has_iommu = iommu_np && of_device_is_compatible(iommu_np, "xen,grant-dma");
+ of_node_put(iommu_np);
+
+ return has_iommu;
+}
+
+void xen_grant_setup_dma_ops(struct device *dev)
+{
+ struct xen_grant_dma_data *data;
+ struct of_phandle_args iommu_spec;
+
+ data = find_xen_grant_dma_data(dev);
+ if (data) {
+ dev_err(dev, "Xen grant DMA data is already created\n");
+ return;
+ }
+
+ /* XXX ACPI device unsupported for now */
+ if (!dev->of_node)
+ goto err;
+
+ if (of_parse_phandle_with_args(dev->of_node, "iommus", "#iommu-cells",
+ 0, &iommu_spec)) {
+ dev_err(dev, "Cannot parse iommus property\n");
+ goto err;
+ }
+
+ if (!of_device_is_compatible(iommu_spec.np, "xen,grant-dma") ||
+ iommu_spec.args_count != 1) {
+ dev_err(dev, "Incompatible IOMMU node\n");
+ of_node_put(iommu_spec.np);
+ goto err;
+ }
+
+ of_node_put(iommu_spec.np);
+
+ data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+ if (!data)
+ goto err;
+
+ /*
+ * The endpoint ID here means the ID of the domain where the corresponding
+ * backend is running
+ */
+ data->backend_domid = iommu_spec.args[0];
+
+ if (xa_err(xa_store(&xen_grant_dma_devices, (unsigned long)dev, data,
+ GFP_KERNEL))) {
+ dev_err(dev, "Cannot store Xen grant DMA data\n");
+ goto err;
+ }
+
+ dev->dma_ops = &xen_grant_dma_ops;
+
+ return;
+
+err:
+ dev_err(dev, "Cannot set up Xen grant DMA ops, retain platform DMA ops\n");
+}
+
+MODULE_DESCRIPTION("Xen grant DMA-mapping layer");
+MODULE_AUTHOR("Juergen Gross <[email protected]>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 7a18292540bc..738029de3c67 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -33,6 +33,7 @@
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
+#include <linux/bitmap.h>
#include <linux/memblock.h>
#include <linux/sched.h>
#include <linux/mm.h>
@@ -70,9 +71,32 @@
static grant_ref_t **gnttab_list;
static unsigned int nr_grant_frames;
+
+/*
+ * Handling of free grants:
+ *
+ * Free grants are in a simple list anchored in gnttab_free_head. They are
+ * linked by grant ref, the last element contains GNTTAB_LIST_END. The number
+ * of free entries is stored in gnttab_free_count.
+ * Additionally there is a bitmap of free entries anchored in
+ * gnttab_free_bitmap. This is being used for simplifying allocation of
+ * multiple consecutive grants, which is needed e.g. for support of virtio.
+ * gnttab_last_free is used to add free entries of new frames at the end of
+ * the free list.
+ * gnttab_free_tail_ptr specifies the variable which references the start
+ * of consecutive free grants ending with gnttab_last_free. This pointer is
+ * updated in a rather defensive way, in order to avoid performance hits in
+ * hot paths.
+ * All those variables are protected by gnttab_list_lock.
+ */
static int gnttab_free_count;
-static grant_ref_t gnttab_free_head;
+static unsigned int gnttab_size;
+static grant_ref_t gnttab_free_head = GNTTAB_LIST_END;
+static grant_ref_t gnttab_last_free = GNTTAB_LIST_END;
+static grant_ref_t *gnttab_free_tail_ptr;
+static unsigned long *gnttab_free_bitmap;
static DEFINE_SPINLOCK(gnttab_list_lock);
+
struct grant_frames xen_auto_xlat_grant_frames;
static unsigned int xen_gnttab_version;
module_param_named(version, xen_gnttab_version, uint, 0);
@@ -168,16 +192,116 @@ static int get_free_entries(unsigned count)
ref = head = gnttab_free_head;
gnttab_free_count -= count;
- while (count-- > 1)
- head = gnttab_entry(head);
+ while (count--) {
+ bitmap_clear(gnttab_free_bitmap, head, 1);
+ if (gnttab_free_tail_ptr == __gnttab_entry(head))
+ gnttab_free_tail_ptr = &gnttab_free_head;
+ if (count)
+ head = gnttab_entry(head);
+ }
gnttab_free_head = gnttab_entry(head);
gnttab_entry(head) = GNTTAB_LIST_END;
+ if (!gnttab_free_count) {
+ gnttab_last_free = GNTTAB_LIST_END;
+ gnttab_free_tail_ptr = NULL;
+ }
+
spin_unlock_irqrestore(&gnttab_list_lock, flags);
return ref;
}
+static int get_seq_entry_count(void)
+{
+ if (gnttab_last_free == GNTTAB_LIST_END || !gnttab_free_tail_ptr ||
+ *gnttab_free_tail_ptr == GNTTAB_LIST_END)
+ return 0;
+
+ return gnttab_last_free - *gnttab_free_tail_ptr + 1;
+}
+
+/* Rebuilds the free grant list and tries to find count consecutive entries. */
+static int get_free_seq(unsigned int count)
+{
+ int ret = -ENOSPC;
+ unsigned int from, to;
+ grant_ref_t *last;
+
+ gnttab_free_tail_ptr = &gnttab_free_head;
+ last = &gnttab_free_head;
+
+ for (from = find_first_bit(gnttab_free_bitmap, gnttab_size);
+ from < gnttab_size;
+ from = find_next_bit(gnttab_free_bitmap, gnttab_size, to + 1)) {
+ to = find_next_zero_bit(gnttab_free_bitmap, gnttab_size,
+ from + 1);
+ if (ret < 0 && to - from >= count) {
+ ret = from;
+ bitmap_clear(gnttab_free_bitmap, ret, count);
+ from += count;
+ gnttab_free_count -= count;
+ if (from == to)
+ continue;
+ }
+
+ /*
+ * Recreate the free list in order to have it properly sorted.
+ * This is needed to make sure that the free tail has the maximum
+ * possible size.
+ */
+ while (from < to) {
+ *last = from;
+ last = __gnttab_entry(from);
+ gnttab_last_free = from;
+ from++;
+ }
+ if (to < gnttab_size)
+ gnttab_free_tail_ptr = __gnttab_entry(to - 1);
+ }
+
+ *last = GNTTAB_LIST_END;
+ if (gnttab_last_free != gnttab_size - 1)
+ gnttab_free_tail_ptr = NULL;
+
+ return ret;
+}
+
+static int get_free_entries_seq(unsigned int count)
+{
+ unsigned long flags;
+ int ret = 0;
+
+ spin_lock_irqsave(&gnttab_list_lock, flags);
+
+ if (gnttab_free_count < count) {
+ ret = gnttab_expand(count - gnttab_free_count);
+ if (ret < 0)
+ goto out;
+ }
+
+ if (get_seq_entry_count() < count) {
+ ret = get_free_seq(count);
+ if (ret >= 0)
+ goto out;
+ ret = gnttab_expand(count - get_seq_entry_count());
+ if (ret < 0)
+ goto out;
+ }
+
+ ret = *gnttab_free_tail_ptr;
+ *gnttab_free_tail_ptr = gnttab_entry(ret + count - 1);
+ gnttab_free_count -= count;
+ if (!gnttab_free_count)
+ gnttab_free_tail_ptr = NULL;
+ bitmap_clear(gnttab_free_bitmap, ret, count);
+
+ out:
+ spin_unlock_irqrestore(&gnttab_list_lock, flags);
+
+ return ret;
+}
+
static void do_free_callbacks(void)
{
struct gnttab_free_callback *callback, *next;
@@ -204,21 +328,51 @@ static inline void check_free_callbacks(void)
do_free_callbacks();
}
-static void put_free_entry(grant_ref_t ref)
+static void put_free_entry_locked(grant_ref_t ref)
{
- unsigned long flags;
-
if (unlikely(ref < GNTTAB_NR_RESERVED_ENTRIES))
return;
- spin_lock_irqsave(&gnttab_list_lock, flags);
gnttab_entry(ref) = gnttab_free_head;
gnttab_free_head = ref;
+ if (!gnttab_free_count)
+ gnttab_last_free = ref;
+ if (gnttab_free_tail_ptr == &gnttab_free_head)
+ gnttab_free_tail_ptr = __gnttab_entry(ref);
gnttab_free_count++;
+ bitmap_set(gnttab_free_bitmap, ref, 1);
+}
+
+static void put_free_entry(grant_ref_t ref)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&gnttab_list_lock, flags);
+ put_free_entry_locked(ref);
check_free_callbacks();
spin_unlock_irqrestore(&gnttab_list_lock, flags);
}
+static void gnttab_set_free(unsigned int start, unsigned int n)
+{
+ unsigned int i;
+
+ for (i = start; i < start + n - 1; i++)
+ gnttab_entry(i) = i + 1;
+
+ gnttab_entry(i) = GNTTAB_LIST_END;
+ if (!gnttab_free_count) {
+ gnttab_free_head = start;
+ gnttab_free_tail_ptr = &gnttab_free_head;
+ } else {
+ gnttab_entry(gnttab_last_free) = start;
+ }
+ gnttab_free_count += n;
+ gnttab_last_free = i;
+
+ bitmap_set(gnttab_free_bitmap, start, n);
+}
+
/*
* Following applies to gnttab_update_entry_v1 and gnttab_update_entry_v2.
* Introducing a valid entry into the grant table:
@@ -450,23 +604,31 @@ void gnttab_free_grant_references(grant_ref_t head)
{
grant_ref_t ref;
unsigned long flags;
- int count = 1;
- if (head == GNTTAB_LIST_END)
- return;
+
spin_lock_irqsave(&gnttab_list_lock, flags);
- ref = head;
- while (gnttab_entry(ref) != GNTTAB_LIST_END) {
- ref = gnttab_entry(ref);
- count++;
+ while (head != GNTTAB_LIST_END) {
+ ref = gnttab_entry(head);
+ put_free_entry_locked(head);
+ head = ref;
}
- gnttab_entry(ref) = gnttab_free_head;
- gnttab_free_head = head;
- gnttab_free_count += count;
check_free_callbacks();
spin_unlock_irqrestore(&gnttab_list_lock, flags);
}
EXPORT_SYMBOL_GPL(gnttab_free_grant_references);
+void gnttab_free_grant_reference_seq(grant_ref_t head, unsigned int count)
+{
+ unsigned long flags;
+ unsigned int i;
+
+ spin_lock_irqsave(&gnttab_list_lock, flags);
+ for (i = count; i > 0; i--)
+ put_free_entry_locked(head + i - 1);
+ check_free_callbacks();
+ spin_unlock_irqrestore(&gnttab_list_lock, flags);
+}
+EXPORT_SYMBOL_GPL(gnttab_free_grant_reference_seq);
+
int gnttab_alloc_grant_references(u16 count, grant_ref_t *head)
{
int h = get_free_entries(count);
@@ -480,6 +642,24 @@ int gnttab_alloc_grant_references(u16 count, grant_ref_t *head)
}
EXPORT_SYMBOL_GPL(gnttab_alloc_grant_references);
+int gnttab_alloc_grant_reference_seq(unsigned int count, grant_ref_t *first)
+{
+ int h;
+
+ if (count == 1)
+ h = get_free_entries(1);
+ else
+ h = get_free_entries_seq(count);
+
+ if (h < 0)
+ return -ENOSPC;
+
+ *first = h;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(gnttab_alloc_grant_reference_seq);
+
int gnttab_empty_grant_references(const grant_ref_t *private_head)
{
return (*private_head == GNTTAB_LIST_END);
@@ -572,16 +752,13 @@ static int grow_gnttab_list(unsigned int more_frames)
goto grow_nomem;
}
+ gnttab_set_free(gnttab_size, extra_entries);
- for (i = grefs_per_frame * nr_grant_frames;
- i < grefs_per_frame * new_nr_grant_frames - 1; i++)
- gnttab_entry(i) = i + 1;
-
- gnttab_entry(i) = gnttab_free_head;
- gnttab_free_head = grefs_per_frame * nr_grant_frames;
- gnttab_free_count += extra_entries;
+ if (!gnttab_free_tail_ptr)
+ gnttab_free_tail_ptr = __gnttab_entry(gnttab_size);
nr_grant_frames = new_nr_grant_frames;
+ gnttab_size += extra_entries;
check_free_callbacks();
@@ -1424,20 +1601,20 @@ static int gnttab_expand(unsigned int req_entries)
int gnttab_init(void)
{
int i;
- unsigned long max_nr_grant_frames;
+ unsigned long max_nr_grant_frames, max_nr_grefs;
unsigned int max_nr_glist_frames, nr_glist_frames;
- unsigned int nr_init_grefs;
int ret;
gnttab_request_version();
max_nr_grant_frames = gnttab_max_grant_frames();
+ max_nr_grefs = max_nr_grant_frames *
+ gnttab_interface->grefs_per_grant_frame;
nr_grant_frames = 1;
/* Determine the maximum number of frames required for the
* grant reference free list on the current hypervisor.
*/
- max_nr_glist_frames = (max_nr_grant_frames *
- gnttab_interface->grefs_per_grant_frame / RPP);
+ max_nr_glist_frames = max_nr_grefs / RPP;
gnttab_list = kmalloc_array(max_nr_glist_frames,
sizeof(grant_ref_t *),
@@ -1454,6 +1631,12 @@ int gnttab_init(void)
}
}
+ gnttab_free_bitmap = bitmap_zalloc(max_nr_grefs, GFP_KERNEL);
+ if (!gnttab_free_bitmap) {
+ ret = -ENOMEM;
+ goto ini_nomem;
+ }
+
ret = arch_gnttab_init(max_nr_grant_frames,
nr_status_frames(max_nr_grant_frames));
if (ret < 0)
@@ -1464,15 +1647,10 @@ int gnttab_init(void)
goto ini_nomem;
}
- nr_init_grefs = nr_grant_frames *
- gnttab_interface->grefs_per_grant_frame;
-
- for (i = GNTTAB_NR_RESERVED_ENTRIES; i < nr_init_grefs - 1; i++)
- gnttab_entry(i) = i + 1;
+ gnttab_size = nr_grant_frames * gnttab_interface->grefs_per_grant_frame;
- gnttab_entry(nr_init_grefs - 1) = GNTTAB_LIST_END;
- gnttab_free_count = nr_init_grefs - GNTTAB_NR_RESERVED_ENTRIES;
- gnttab_free_head = GNTTAB_NR_RESERVED_ENTRIES;
+ gnttab_set_free(GNTTAB_NR_RESERVED_ENTRIES,
+ gnttab_size - GNTTAB_NR_RESERVED_ENTRIES);
printk("Grant table initialized\n");
return 0;
@@ -1481,6 +1659,7 @@ int gnttab_init(void)
for (i--; i >= 0; i--)
free_page((unsigned long)gnttab_list[i]);
kfree(gnttab_list);
+ bitmap_free(gnttab_free_bitmap);
return ret;
}
EXPORT_SYMBOL_GPL(gnttab_init);
diff --git a/drivers/xen/xlate_mmu.c b/drivers/xen/xlate_mmu.c
index 34742c6e189e..f17c4c03db30 100644
--- a/drivers/xen/xlate_mmu.c
+++ b/drivers/xen/xlate_mmu.c
@@ -261,7 +261,6 @@ int __init xen_xlate_map_ballooned_pages(xen_pfn_t **gfns, void **virt,
return 0;
}
-EXPORT_SYMBOL_GPL(xen_xlate_map_ballooned_pages);
struct remap_pfn {
struct mm_struct *mm;
diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index 1c8dc696d516..cebba4eaa0b5 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -62,12 +62,12 @@ void v9fs_cache_inode_get_cookie(struct inode *inode)
version = cpu_to_le32(v9inode->qid.version);
path = cpu_to_le64(v9inode->qid.path);
v9ses = v9fs_inode2v9ses(inode);
- v9inode->netfs_ctx.cache =
+ v9inode->netfs.cache =
fscache_acquire_cookie(v9fs_session_cache(v9ses),
0,
&path, sizeof(path),
&version, sizeof(version),
- i_size_read(&v9inode->vfs_inode));
+ i_size_read(&v9inode->netfs.inode));
p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n",
inode, v9fs_inode_cookie(v9inode));
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index e28ddf763b3b..0129de2ea31a 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -625,7 +625,7 @@ static void v9fs_inode_init_once(void *foo)
struct v9fs_inode *v9inode = (struct v9fs_inode *)foo;
memset(&v9inode->qid, 0, sizeof(v9inode->qid));
- inode_init_once(&v9inode->vfs_inode);
+ inode_init_once(&v9inode->netfs.inode);
}
/**
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index ec0e8df3b2eb..1b219c21d15e 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -109,11 +109,7 @@ struct v9fs_session_info {
#define V9FS_INO_INVALID_ATTR 0x01
struct v9fs_inode {
- struct {
- /* These must be contiguous */
- struct inode vfs_inode; /* the VFS's inode record */
- struct netfs_i_context netfs_ctx; /* Netfslib context */
- };
+ struct netfs_inode netfs; /* Netfslib context and vfs inode */
struct p9_qid qid;
unsigned int cache_validity;
struct p9_fid *writeback_fid;
@@ -122,13 +118,13 @@ struct v9fs_inode {
static inline struct v9fs_inode *V9FS_I(const struct inode *inode)
{
- return container_of(inode, struct v9fs_inode, vfs_inode);
+ return container_of(inode, struct v9fs_inode, netfs.inode);
}
static inline struct fscache_cookie *v9fs_inode_cookie(struct v9fs_inode *v9inode)
{
#ifdef CONFIG_9P_FSCACHE
- return netfs_i_cookie(&v9inode->vfs_inode);
+ return netfs_i_cookie(&v9inode->netfs.inode);
#else
return NULL;
#endif
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 8ce82ff1e40a..90c6c1ba03ab 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -140,7 +140,7 @@ static void v9fs_write_to_cache_done(void *priv, ssize_t transferred_or_error,
transferred_or_error != -ENOBUFS) {
version = cpu_to_le32(v9inode->qid.version);
fscache_invalidate(v9fs_inode_cookie(v9inode), &version,
- i_size_read(&v9inode->vfs_inode), 0);
+ i_size_read(&v9inode->netfs.inode), 0);
}
}
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 55367ecb9442..e660c6348b9d 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -234,7 +234,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb)
v9inode->writeback_fid = NULL;
v9inode->cache_validity = 0;
mutex_init(&v9inode->v_mutex);
- return &v9inode->vfs_inode;
+ return &v9inode->netfs.inode;
}
/**
@@ -252,7 +252,7 @@ void v9fs_free_inode(struct inode *inode)
*/
static void v9fs_set_netfs_context(struct inode *inode)
{
- netfs_i_context_init(inode, &v9fs_req_ops);
+ netfs_inode_init(inode, &v9fs_req_ops);
}
int v9fs_init_inode(struct v9fs_session_info *v9ses,
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 1b4d5809808d..a484fa642808 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -30,7 +30,7 @@ void afs_invalidate_mmap_work(struct work_struct *work)
{
struct afs_vnode *vnode = container_of(work, struct afs_vnode, cb_work);
- unmap_mapping_pages(vnode->vfs_inode.i_mapping, 0, 0, false);
+ unmap_mapping_pages(vnode->netfs.inode.i_mapping, 0, 0, false);
}
void afs_server_init_callback_work(struct work_struct *work)
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 79f6b74336d2..56ae5cd5184f 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -109,7 +109,7 @@ struct afs_lookup_cookie {
*/
static void afs_dir_read_cleanup(struct afs_read *req)
{
- struct address_space *mapping = req->vnode->vfs_inode.i_mapping;
+ struct address_space *mapping = req->vnode->netfs.inode.i_mapping;
struct folio *folio;
pgoff_t last = req->nr_pages - 1;
@@ -153,7 +153,7 @@ static bool afs_dir_check_folio(struct afs_vnode *dvnode, struct folio *folio,
block = kmap_local_folio(folio, offset);
if (block->hdr.magic != AFS_DIR_MAGIC) {
printk("kAFS: %s(%lx): [%llx] bad magic %zx/%zx is %04hx\n",
- __func__, dvnode->vfs_inode.i_ino,
+ __func__, dvnode->netfs.inode.i_ino,
pos, offset, size, ntohs(block->hdr.magic));
trace_afs_dir_check_failed(dvnode, pos + offset, i_size);
kunmap_local(block);
@@ -183,7 +183,7 @@ error:
static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req)
{
union afs_xdr_dir_block *block;
- struct address_space *mapping = dvnode->vfs_inode.i_mapping;
+ struct address_space *mapping = dvnode->netfs.inode.i_mapping;
struct folio *folio;
pgoff_t last = req->nr_pages - 1;
size_t offset, size;
@@ -217,7 +217,7 @@ static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req)
*/
static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req)
{
- struct address_space *mapping = dvnode->vfs_inode.i_mapping;
+ struct address_space *mapping = dvnode->netfs.inode.i_mapping;
struct folio *folio;
pgoff_t last = req->nr_pages - 1;
int ret = 0;
@@ -269,7 +269,7 @@ static int afs_dir_open(struct inode *inode, struct file *file)
static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
__acquires(&dvnode->validate_lock)
{
- struct address_space *mapping = dvnode->vfs_inode.i_mapping;
+ struct address_space *mapping = dvnode->netfs.inode.i_mapping;
struct afs_read *req;
loff_t i_size;
int nr_pages, i;
@@ -287,7 +287,7 @@ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
req->cleanup = afs_dir_read_cleanup;
expand:
- i_size = i_size_read(&dvnode->vfs_inode);
+ i_size = i_size_read(&dvnode->netfs.inode);
if (i_size < 2048) {
ret = afs_bad(dvnode, afs_file_error_dir_small);
goto error;
@@ -305,7 +305,7 @@ expand:
req->actual_len = i_size; /* May change */
req->len = nr_pages * PAGE_SIZE; /* We can ask for more than there is */
req->data_version = dvnode->status.data_version; /* May change */
- iov_iter_xarray(&req->def_iter, READ, &dvnode->vfs_inode.i_mapping->i_pages,
+ iov_iter_xarray(&req->def_iter, READ, &dvnode->netfs.inode.i_mapping->i_pages,
0, i_size);
req->iter = &req->def_iter;
@@ -897,7 +897,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
out_op:
if (op->error == 0) {
- inode = &op->file[1].vnode->vfs_inode;
+ inode = &op->file[1].vnode->netfs.inode;
op->file[1].vnode = NULL;
}
@@ -1139,7 +1139,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
afs_stat_v(dir, n_reval);
/* search the directory for this vnode */
- ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key, &dir_version);
+ ret = afs_do_lookup_one(&dir->netfs.inode, dentry, &fid, key, &dir_version);
switch (ret) {
case 0:
/* the filename maps to something */
@@ -1170,7 +1170,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
_debug("%pd: file deleted (uq %u -> %u I:%u)",
dentry, fid.unique,
vnode->fid.unique,
- vnode->vfs_inode.i_generation);
+ vnode->netfs.inode.i_generation);
goto not_found;
}
goto out_valid;
@@ -1368,7 +1368,7 @@ static void afs_dir_remove_subdir(struct dentry *dentry)
if (d_really_is_positive(dentry)) {
struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
- clear_nlink(&vnode->vfs_inode);
+ clear_nlink(&vnode->netfs.inode);
set_bit(AFS_VNODE_DELETED, &vnode->flags);
clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
@@ -1487,8 +1487,8 @@ static void afs_dir_remove_link(struct afs_operation *op)
/* Already done */
} else if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {
write_seqlock(&vnode->cb_lock);
- drop_nlink(&vnode->vfs_inode);
- if (vnode->vfs_inode.i_nlink == 0) {
+ drop_nlink(&vnode->netfs.inode);
+ if (vnode->netfs.inode.i_nlink == 0) {
set_bit(AFS_VNODE_DELETED, &vnode->flags);
__afs_break_callback(vnode, afs_cb_break_for_unlink);
}
@@ -1504,7 +1504,7 @@ static void afs_dir_remove_link(struct afs_operation *op)
op->error = ret;
}
- _debug("nlink %d [val %d]", vnode->vfs_inode.i_nlink, op->error);
+ _debug("nlink %d [val %d]", vnode->netfs.inode.i_nlink, op->error);
}
static void afs_unlink_success(struct afs_operation *op)
@@ -1680,8 +1680,8 @@ static void afs_link_success(struct afs_operation *op)
afs_update_dentry_version(op, dvp, op->dentry);
if (op->dentry_2->d_parent == op->dentry->d_parent)
afs_update_dentry_version(op, dvp, op->dentry_2);
- ihold(&vp->vnode->vfs_inode);
- d_instantiate(op->dentry, &vp->vnode->vfs_inode);
+ ihold(&vp->vnode->netfs.inode);
+ d_instantiate(op->dentry, &vp->vnode->netfs.inode);
}
static void afs_link_put(struct afs_operation *op)
diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c
index d98e109ecee9..0ab7752d1b75 100644
--- a/fs/afs/dir_edit.c
+++ b/fs/afs/dir_edit.c
@@ -109,7 +109,7 @@ static void afs_clear_contig_bits(union afs_xdr_dir_block *block,
*/
static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index)
{
- struct address_space *mapping = vnode->vfs_inode.i_mapping;
+ struct address_space *mapping = vnode->netfs.inode.i_mapping;
struct folio *folio;
folio = __filemap_get_folio(mapping, index,
@@ -216,7 +216,7 @@ void afs_edit_dir_add(struct afs_vnode *vnode,
_enter(",,{%d,%s},", name->len, name->name);
- i_size = i_size_read(&vnode->vfs_inode);
+ i_size = i_size_read(&vnode->netfs.inode);
if (i_size > AFS_DIR_BLOCK_SIZE * AFS_DIR_MAX_BLOCKS ||
(i_size & (AFS_DIR_BLOCK_SIZE - 1))) {
clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
@@ -336,7 +336,7 @@ found_space:
if (b < AFS_DIR_BLOCKS_WITH_CTR)
meta->meta.alloc_ctrs[b] -= need_slots;
- inode_inc_iversion_raw(&vnode->vfs_inode);
+ inode_inc_iversion_raw(&vnode->netfs.inode);
afs_stat_v(vnode, n_dir_cr);
_debug("Insert %s in %u[%u]", name->name, b, slot);
@@ -383,7 +383,7 @@ void afs_edit_dir_remove(struct afs_vnode *vnode,
_enter(",,{%d,%s},", name->len, name->name);
- i_size = i_size_read(&vnode->vfs_inode);
+ i_size = i_size_read(&vnode->netfs.inode);
if (i_size < AFS_DIR_BLOCK_SIZE ||
i_size > AFS_DIR_BLOCK_SIZE * AFS_DIR_MAX_BLOCKS ||
(i_size & (AFS_DIR_BLOCK_SIZE - 1))) {
@@ -463,7 +463,7 @@ found_dirent:
if (b < AFS_DIR_BLOCKS_WITH_CTR)
meta->meta.alloc_ctrs[b] += need_slots;
- inode_set_iversion_raw(&vnode->vfs_inode, vnode->status.data_version);
+ inode_set_iversion_raw(&vnode->netfs.inode, vnode->status.data_version);
afs_stat_v(vnode, n_dir_rm);
_debug("Remove %s from %u[%u]", name->name, b, slot);
diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c
index 45cfd50a9521..bb5807e87fa4 100644
--- a/fs/afs/dir_silly.c
+++ b/fs/afs/dir_silly.c
@@ -131,7 +131,7 @@ int afs_sillyrename(struct afs_vnode *dvnode, struct afs_vnode *vnode,
goto out;
} while (!d_is_negative(sdentry));
- ihold(&vnode->vfs_inode);
+ ihold(&vnode->netfs.inode);
ret = afs_do_silly_rename(dvnode, vnode, dentry, sdentry, key);
switch (ret) {
@@ -148,7 +148,7 @@ int afs_sillyrename(struct afs_vnode *dvnode, struct afs_vnode *vnode,
d_drop(sdentry);
}
- iput(&vnode->vfs_inode);
+ iput(&vnode->netfs.inode);
dput(sdentry);
out:
_leave(" = %d", ret);
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index f120bcb8bf73..3a5bbffdf053 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -76,7 +76,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root)
/* there shouldn't be an existing inode */
BUG_ON(!(inode->i_state & I_NEW));
- netfs_i_context_init(inode, NULL);
+ netfs_inode_init(inode, NULL);
inode->i_size = 0;
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
if (root) {
diff --git a/fs/afs/file.c b/fs/afs/file.c
index a8e8832179e4..4de7af7c2f09 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -194,7 +194,7 @@ int afs_release(struct inode *inode, struct file *file)
afs_put_wb_key(af->wb);
if ((file->f_mode & FMODE_WRITE)) {
- i_size = i_size_read(&vnode->vfs_inode);
+ i_size = i_size_read(&vnode->netfs.inode);
afs_set_cache_aux(vnode, &aux);
fscache_unuse_cookie(afs_vnode_cache(vnode), &aux, &i_size);
} else {
@@ -325,7 +325,7 @@ static void afs_issue_read(struct netfs_io_subrequest *subreq)
fsreq->iter = &fsreq->def_iter;
iov_iter_xarray(&fsreq->def_iter, READ,
- &fsreq->vnode->vfs_inode.i_mapping->i_pages,
+ &fsreq->vnode->netfs.inode.i_mapping->i_pages,
fsreq->pos, fsreq->len);
afs_fetch_data(fsreq->vnode, fsreq);
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index d222dfbe976b..7a3803ce3a22 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -232,14 +232,14 @@ int afs_put_operation(struct afs_operation *op)
if (op->file[1].modification && op->file[1].vnode != op->file[0].vnode)
clear_bit(AFS_VNODE_MODIFYING, &op->file[1].vnode->flags);
if (op->file[0].put_vnode)
- iput(&op->file[0].vnode->vfs_inode);
+ iput(&op->file[0].vnode->netfs.inode);
if (op->file[1].put_vnode)
- iput(&op->file[1].vnode->vfs_inode);
+ iput(&op->file[1].vnode->netfs.inode);
if (op->more_files) {
for (i = 0; i < op->nr_files - 2; i++)
if (op->more_files[i].put_vnode)
- iput(&op->more_files[i].vnode->vfs_inode);
+ iput(&op->more_files[i].vnode->netfs.inode);
kfree(op->more_files);
}
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 65b439cd53d2..22811e9eacf5 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -25,9 +25,6 @@
#include "internal.h"
#include "afs_fs.h"
-// Temporary: netfs does disgusting things with inode pointers
-#pragma GCC diagnostic ignored "-Wattribute-warning"
-
static const struct inode_operations afs_symlink_inode_operations = {
.get_link = page_get_link,
};
@@ -61,7 +58,7 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren
*/
static void afs_set_netfs_context(struct afs_vnode *vnode)
{
- netfs_i_context_init(&vnode->vfs_inode, &afs_req_ops);
+ netfs_inode_init(&vnode->netfs.inode, &afs_req_ops);
}
/*
@@ -99,7 +96,7 @@ static int afs_inode_init_from_status(struct afs_operation *op,
inode->i_flags |= S_NOATIME;
inode->i_uid = make_kuid(&init_user_ns, status->owner);
inode->i_gid = make_kgid(&init_user_ns, status->group);
- set_nlink(&vnode->vfs_inode, status->nlink);
+ set_nlink(&vnode->netfs.inode, status->nlink);
switch (status->type) {
case AFS_FTYPE_FILE:
@@ -142,7 +139,7 @@ static int afs_inode_init_from_status(struct afs_operation *op,
afs_set_netfs_context(vnode);
vnode->invalid_before = status->data_version;
- inode_set_iversion_raw(&vnode->vfs_inode, status->data_version);
+ inode_set_iversion_raw(&vnode->netfs.inode, status->data_version);
if (!vp->scb.have_cb) {
/* it's a symlink we just created (the fileserver
@@ -166,7 +163,7 @@ static void afs_apply_status(struct afs_operation *op,
{
struct afs_file_status *status = &vp->scb.status;
struct afs_vnode *vnode = vp->vnode;
- struct inode *inode = &vnode->vfs_inode;
+ struct inode *inode = &vnode->netfs.inode;
struct timespec64 t;
umode_t mode;
bool data_changed = false;
@@ -249,7 +246,7 @@ static void afs_apply_status(struct afs_operation *op,
* idea of what the size should be that's not the same as
* what's on the server.
*/
- vnode->netfs_ctx.remote_i_size = status->size;
+ vnode->netfs.remote_i_size = status->size;
if (change_size) {
afs_set_i_size(vnode, status->size);
inode->i_ctime = t;
@@ -292,7 +289,7 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v
*/
if (vp->scb.status.abort_code == VNOVNODE) {
set_bit(AFS_VNODE_DELETED, &vnode->flags);
- clear_nlink(&vnode->vfs_inode);
+ clear_nlink(&vnode->netfs.inode);
__afs_break_callback(vnode, afs_cb_break_for_deleted);
op->flags &= ~AFS_OPERATION_DIR_CONFLICT;
}
@@ -309,8 +306,8 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v
if (vp->scb.have_cb)
afs_apply_callback(op, vp);
} else if (vp->op_unlinked && !(op->flags & AFS_OPERATION_DIR_CONFLICT)) {
- drop_nlink(&vnode->vfs_inode);
- if (vnode->vfs_inode.i_nlink == 0) {
+ drop_nlink(&vnode->netfs.inode);
+ if (vnode->netfs.inode.i_nlink == 0) {
set_bit(AFS_VNODE_DELETED, &vnode->flags);
__afs_break_callback(vnode, afs_cb_break_for_deleted);
}
@@ -329,7 +326,7 @@ static void afs_fetch_status_success(struct afs_operation *op)
struct afs_vnode *vnode = vp->vnode;
int ret;
- if (vnode->vfs_inode.i_state & I_NEW) {
+ if (vnode->netfs.inode.i_state & I_NEW) {
ret = afs_inode_init_from_status(op, vp, vnode);
op->error = ret;
if (ret == 0)
@@ -433,7 +430,7 @@ static void afs_get_inode_cache(struct afs_vnode *vnode)
struct afs_vnode_cache_aux aux;
if (vnode->status.type != AFS_FTYPE_FILE) {
- vnode->netfs_ctx.cache = NULL;
+ vnode->netfs.cache = NULL;
return;
}
@@ -460,7 +457,7 @@ static void afs_get_inode_cache(struct afs_vnode *vnode)
struct inode *afs_iget(struct afs_operation *op, struct afs_vnode_param *vp)
{
struct afs_vnode_param *dvp = &op->file[0];
- struct super_block *sb = dvp->vnode->vfs_inode.i_sb;
+ struct super_block *sb = dvp->vnode->netfs.inode.i_sb;
struct afs_vnode *vnode;
struct inode *inode;
int ret;
@@ -585,10 +582,10 @@ static void afs_zap_data(struct afs_vnode *vnode)
/* nuke all the non-dirty pages that aren't locked, mapped or being
* written back in a regular file and completely discard the pages in a
* directory or symlink */
- if (S_ISREG(vnode->vfs_inode.i_mode))
- invalidate_remote_inode(&vnode->vfs_inode);
+ if (S_ISREG(vnode->netfs.inode.i_mode))
+ invalidate_remote_inode(&vnode->netfs.inode);
else
- invalidate_inode_pages2(vnode->vfs_inode.i_mapping);
+ invalidate_inode_pages2(vnode->netfs.inode.i_mapping);
}
/*
@@ -686,8 +683,8 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
key_serial(key));
if (unlikely(test_bit(AFS_VNODE_DELETED, &vnode->flags))) {
- if (vnode->vfs_inode.i_nlink)
- clear_nlink(&vnode->vfs_inode);
+ if (vnode->netfs.inode.i_nlink)
+ clear_nlink(&vnode->netfs.inode);
goto valid;
}
@@ -829,7 +826,7 @@ void afs_evict_inode(struct inode *inode)
static void afs_setattr_success(struct afs_operation *op)
{
struct afs_vnode_param *vp = &op->file[0];
- struct inode *inode = &vp->vnode->vfs_inode;
+ struct inode *inode = &vp->vnode->netfs.inode;
loff_t old_i_size = i_size_read(inode);
op->setattr.old_i_size = old_i_size;
@@ -846,7 +843,7 @@ static void afs_setattr_success(struct afs_operation *op)
static void afs_setattr_edit_file(struct afs_operation *op)
{
struct afs_vnode_param *vp = &op->file[0];
- struct inode *inode = &vp->vnode->vfs_inode;
+ struct inode *inode = &vp->vnode->netfs.inode;
if (op->setattr.attr->ia_valid & ATTR_SIZE) {
loff_t size = op->setattr.attr->ia_size;
@@ -878,7 +875,7 @@ int afs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
ATTR_MTIME | ATTR_MTIME_SET | ATTR_TIMES_SET | ATTR_TOUCH;
struct afs_operation *op;
struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
- struct inode *inode = &vnode->vfs_inode;
+ struct inode *inode = &vnode->netfs.inode;
loff_t i_size;
int ret;
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index a30995901266..984b113a9107 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -619,12 +619,7 @@ enum afs_lock_state {
* leak from one inode to another.
*/
struct afs_vnode {
- struct {
- /* These must be contiguous */
- struct inode vfs_inode; /* the VFS's inode record */
- struct netfs_i_context netfs_ctx; /* Netfslib context */
- };
-
+ struct netfs_inode netfs; /* Netfslib context and vfs inode */
struct afs_volume *volume; /* volume on which vnode resides */
struct afs_fid fid; /* the file identifier for this inode */
struct afs_file_status status; /* AFS status info for this file */
@@ -675,7 +670,7 @@ struct afs_vnode {
static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode)
{
#ifdef CONFIG_AFS_FSCACHE
- return netfs_i_cookie(&vnode->vfs_inode);
+ return netfs_i_cookie(&vnode->netfs.inode);
#else
return NULL;
#endif
@@ -685,7 +680,7 @@ static inline void afs_vnode_set_cache(struct afs_vnode *vnode,
struct fscache_cookie *cookie)
{
#ifdef CONFIG_AFS_FSCACHE
- vnode->netfs_ctx.cache = cookie;
+ vnode->netfs.cache = cookie;
#endif
}
@@ -892,7 +887,7 @@ static inline void afs_invalidate_cache(struct afs_vnode *vnode, unsigned int fl
afs_set_cache_aux(vnode, &aux);
fscache_invalidate(afs_vnode_cache(vnode), &aux,
- i_size_read(&vnode->vfs_inode), flags);
+ i_size_read(&vnode->netfs.inode), flags);
}
/*
@@ -1217,7 +1212,7 @@ static inline struct afs_net *afs_i2net(struct inode *inode)
static inline struct afs_net *afs_v2net(struct afs_vnode *vnode)
{
- return afs_i2net(&vnode->vfs_inode);
+ return afs_i2net(&vnode->netfs.inode);
}
static inline struct afs_net *afs_sock2net(struct sock *sk)
@@ -1593,12 +1588,12 @@ extern void yfs_fs_store_opaque_acl2(struct afs_operation *);
*/
static inline struct afs_vnode *AFS_FS_I(struct inode *inode)
{
- return container_of(inode, struct afs_vnode, vfs_inode);
+ return container_of(inode, struct afs_vnode, netfs.inode);
}
static inline struct inode *AFS_VNODE_TO_I(struct afs_vnode *vnode)
{
- return &vnode->vfs_inode;
+ return &vnode->netfs.inode;
}
/*
@@ -1621,8 +1616,8 @@ static inline void afs_update_dentry_version(struct afs_operation *op,
*/
static inline void afs_set_i_size(struct afs_vnode *vnode, u64 size)
{
- i_size_write(&vnode->vfs_inode, size);
- vnode->vfs_inode.i_blocks = ((size + 1023) >> 10) << 1;
+ i_size_write(&vnode->netfs.inode, size);
+ vnode->netfs.inode.i_blocks = ((size + 1023) >> 10) << 1;
}
/*
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 1fea195b0b27..95d713074dc8 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -659,7 +659,7 @@ static void afs_i_init_once(void *_vnode)
struct afs_vnode *vnode = _vnode;
memset(vnode, 0, sizeof(*vnode));
- inode_init_once(&vnode->vfs_inode);
+ inode_init_once(&vnode->netfs.inode);
mutex_init(&vnode->io_lock);
init_rwsem(&vnode->validate_lock);
spin_lock_init(&vnode->wb_lock);
@@ -700,8 +700,8 @@ static struct inode *afs_alloc_inode(struct super_block *sb)
init_rwsem(&vnode->rmdir_lock);
INIT_WORK(&vnode->cb_work, afs_invalidate_mmap_work);
- _leave(" = %p", &vnode->vfs_inode);
- return &vnode->vfs_inode;
+ _leave(" = %p", &vnode->netfs.inode);
+ return &vnode->netfs.inode;
}
static void afs_free_inode(struct inode *inode)
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 2236b2165e37..f80a6096d91c 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -146,10 +146,10 @@ int afs_write_end(struct file *file, struct address_space *mapping,
write_end_pos = pos + copied;
- i_size = i_size_read(&vnode->vfs_inode);
+ i_size = i_size_read(&vnode->netfs.inode);
if (write_end_pos > i_size) {
write_seqlock(&vnode->cb_lock);
- i_size = i_size_read(&vnode->vfs_inode);
+ i_size = i_size_read(&vnode->netfs.inode);
if (write_end_pos > i_size)
afs_set_i_size(vnode, write_end_pos);
write_sequnlock(&vnode->cb_lock);
@@ -257,7 +257,7 @@ static void afs_redirty_pages(struct writeback_control *wbc,
*/
static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len)
{
- struct address_space *mapping = vnode->vfs_inode.i_mapping;
+ struct address_space *mapping = vnode->netfs.inode.i_mapping;
struct folio *folio;
pgoff_t end;
@@ -354,7 +354,6 @@ static const struct afs_operation_ops afs_store_data_operation = {
static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t pos,
bool laundering)
{
- struct netfs_i_context *ictx = &vnode->netfs_ctx;
struct afs_operation *op;
struct afs_wb_key *wbk = NULL;
loff_t size = iov_iter_count(iter);
@@ -385,9 +384,9 @@ static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t
op->store.write_iter = iter;
op->store.pos = pos;
op->store.size = size;
- op->store.i_size = max(pos + size, ictx->remote_i_size);
+ op->store.i_size = max(pos + size, vnode->netfs.remote_i_size);
op->store.laundering = laundering;
- op->mtime = vnode->vfs_inode.i_mtime;
+ op->mtime = vnode->netfs.inode.i_mtime;
op->flags |= AFS_OPERATION_UNINTR;
op->ops = &afs_store_data_operation;
@@ -554,7 +553,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
struct iov_iter iter;
unsigned long priv;
unsigned int offset, to, len, max_len;
- loff_t i_size = i_size_read(&vnode->vfs_inode);
+ loff_t i_size = i_size_read(&vnode->netfs.inode);
bool new_content = test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
bool caching = fscache_cookie_enabled(afs_vnode_cache(vnode));
long count = wbc->nr_to_write;
@@ -845,7 +844,7 @@ ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from)
_enter("{%llx:%llu},{%zu},",
vnode->fid.vid, vnode->fid.vnode, count);
- if (IS_SWAPFILE(&vnode->vfs_inode)) {
+ if (IS_SWAPFILE(&vnode->netfs.inode)) {
printk(KERN_INFO
"AFS: Attempt to write to active swap file!\n");
return -EBUSY;
@@ -958,8 +957,8 @@ void afs_prune_wb_keys(struct afs_vnode *vnode)
/* Discard unused keys */
spin_lock(&vnode->wb_lock);
- if (!mapping_tagged(&vnode->vfs_inode.i_data, PAGECACHE_TAG_WRITEBACK) &&
- !mapping_tagged(&vnode->vfs_inode.i_data, PAGECACHE_TAG_DIRTY)) {
+ if (!mapping_tagged(&vnode->netfs.inode.i_data, PAGECACHE_TAG_WRITEBACK) &&
+ !mapping_tagged(&vnode->netfs.inode.i_data, PAGECACHE_TAG_DIRTY)) {
list_for_each_entry_safe(wbk, tmp, &vnode->wb_keys, vnode_link) {
if (refcount_read(&wbk->usage) == 1)
list_move(&wbk->vnode_link, &graveyard);
@@ -1034,6 +1033,6 @@ static void afs_write_to_cache(struct afs_vnode *vnode,
bool caching)
{
fscache_write_to_cache(afs_vnode_cache(vnode),
- vnode->vfs_inode.i_mapping, start, len, i_size,
+ vnode->netfs.inode.i_mapping, start, len, i_size,
afs_write_to_cache_done, vnode, caching);
}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e5221be6eb55..f5f116ed1b9e 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1798,7 +1798,7 @@ enum {
static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
s64 pool, struct ceph_string *pool_ns)
{
- struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->vfs_inode);
+ struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->netfs.inode);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_osd_request *rd_req = NULL, *wr_req = NULL;
struct rb_node **p, *parent;
@@ -1913,7 +1913,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
0, false, true);
err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
- wr_req->r_mtime = ci->vfs_inode.i_mtime;
+ wr_req->r_mtime = ci->netfs.inode.i_mtime;
err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
if (!err)
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index ddea99922073..177d8e8d73fe 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -29,9 +29,9 @@ void ceph_fscache_register_inode_cookie(struct inode *inode)
if (!(inode->i_state & I_NEW))
return;
- WARN_ON_ONCE(ci->netfs_ctx.cache);
+ WARN_ON_ONCE(ci->netfs.cache);
- ci->netfs_ctx.cache =
+ ci->netfs.cache =
fscache_acquire_cookie(fsc->fscache, 0,
&ci->i_vino, sizeof(ci->i_vino),
&ci->i_version, sizeof(ci->i_version),
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index 7255b790a4c1..26c6ae06e2f4 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -28,7 +28,7 @@ void ceph_fscache_invalidate(struct inode *inode, bool dio_write);
static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci)
{
- return netfs_i_cookie(&ci->vfs_inode);
+ return netfs_i_cookie(&ci->netfs.inode);
}
static inline void ceph_fscache_resize(struct inode *inode, loff_t to)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index bf2e94005598..38c930384d41 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -492,7 +492,7 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
struct ceph_mount_options *opt = mdsc->fsc->mount_options;
ci->i_hold_caps_max = round_jiffies(jiffies +
opt->caps_wanted_delay_max * HZ);
- dout("__cap_set_timeouts %p %lu\n", &ci->vfs_inode,
+ dout("__cap_set_timeouts %p %lu\n", &ci->netfs.inode,
ci->i_hold_caps_max - jiffies);
}
@@ -507,7 +507,7 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
struct ceph_inode_info *ci)
{
- dout("__cap_delay_requeue %p flags 0x%lx at %lu\n", &ci->vfs_inode,
+ dout("__cap_delay_requeue %p flags 0x%lx at %lu\n", &ci->netfs.inode,
ci->i_ceph_flags, ci->i_hold_caps_max);
if (!mdsc->stopping) {
spin_lock(&mdsc->cap_delay_lock);
@@ -531,7 +531,7 @@ no_change:
static void __cap_delay_requeue_front(struct ceph_mds_client *mdsc,
struct ceph_inode_info *ci)
{
- dout("__cap_delay_requeue_front %p\n", &ci->vfs_inode);
+ dout("__cap_delay_requeue_front %p\n", &ci->netfs.inode);
spin_lock(&mdsc->cap_delay_lock);
ci->i_ceph_flags |= CEPH_I_FLUSH;
if (!list_empty(&ci->i_cap_delay_list))
@@ -548,7 +548,7 @@ static void __cap_delay_requeue_front(struct ceph_mds_client *mdsc,
static void __cap_delay_cancel(struct ceph_mds_client *mdsc,
struct ceph_inode_info *ci)
{
- dout("__cap_delay_cancel %p\n", &ci->vfs_inode);
+ dout("__cap_delay_cancel %p\n", &ci->netfs.inode);
if (list_empty(&ci->i_cap_delay_list))
return;
spin_lock(&mdsc->cap_delay_lock);
@@ -568,7 +568,7 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
* Each time we receive FILE_CACHE anew, we increment
* i_rdcache_gen.
*/
- if (S_ISREG(ci->vfs_inode.i_mode) &&
+ if (S_ISREG(ci->netfs.inode.i_mode) &&
(issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
(had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0) {
ci->i_rdcache_gen++;
@@ -583,14 +583,14 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
if ((issued & CEPH_CAP_FILE_SHARED) != (had & CEPH_CAP_FILE_SHARED)) {
if (issued & CEPH_CAP_FILE_SHARED)
atomic_inc(&ci->i_shared_gen);
- if (S_ISDIR(ci->vfs_inode.i_mode)) {
- dout(" marking %p NOT complete\n", &ci->vfs_inode);
+ if (S_ISDIR(ci->netfs.inode.i_mode)) {
+ dout(" marking %p NOT complete\n", &ci->netfs.inode);
__ceph_dir_clear_complete(ci);
}
}
/* Wipe saved layout if we're losing DIR_CREATE caps */
- if (S_ISDIR(ci->vfs_inode.i_mode) && (had & CEPH_CAP_DIR_CREATE) &&
+ if (S_ISDIR(ci->netfs.inode.i_mode) && (had & CEPH_CAP_DIR_CREATE) &&
!(issued & CEPH_CAP_DIR_CREATE)) {
ceph_put_string(rcu_dereference_raw(ci->i_cached_layout.pool_ns));
memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout));
@@ -771,7 +771,7 @@ static int __cap_is_valid(struct ceph_cap *cap)
if (cap->cap_gen < gen || time_after_eq(jiffies, ttl)) {
dout("__cap_is_valid %p cap %p issued %s "
- "but STALE (gen %u vs %u)\n", &cap->ci->vfs_inode,
+ "but STALE (gen %u vs %u)\n", &cap->ci->netfs.inode,
cap, ceph_cap_string(cap->issued), cap->cap_gen, gen);
return 0;
}
@@ -797,7 +797,7 @@ int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented)
if (!__cap_is_valid(cap))
continue;
dout("__ceph_caps_issued %p cap %p issued %s\n",
- &ci->vfs_inode, cap, ceph_cap_string(cap->issued));
+ &ci->netfs.inode, cap, ceph_cap_string(cap->issued));
have |= cap->issued;
if (implemented)
*implemented |= cap->implemented;
@@ -844,12 +844,12 @@ static void __touch_cap(struct ceph_cap *cap)
spin_lock(&s->s_cap_lock);
if (!s->s_cap_iterator) {
- dout("__touch_cap %p cap %p mds%d\n", &cap->ci->vfs_inode, cap,
+ dout("__touch_cap %p cap %p mds%d\n", &cap->ci->netfs.inode, cap,
s->s_mds);
list_move_tail(&cap->session_caps, &s->s_caps);
} else {
dout("__touch_cap %p cap %p mds%d NOP, iterating over caps\n",
- &cap->ci->vfs_inode, cap, s->s_mds);
+ &cap->ci->netfs.inode, cap, s->s_mds);
}
spin_unlock(&s->s_cap_lock);
}
@@ -867,7 +867,7 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
if ((have & mask) == mask) {
dout("__ceph_caps_issued_mask ino 0x%llx snap issued %s"
- " (mask %s)\n", ceph_ino(&ci->vfs_inode),
+ " (mask %s)\n", ceph_ino(&ci->netfs.inode),
ceph_cap_string(have),
ceph_cap_string(mask));
return 1;
@@ -879,7 +879,7 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
continue;
if ((cap->issued & mask) == mask) {
dout("__ceph_caps_issued_mask ino 0x%llx cap %p issued %s"
- " (mask %s)\n", ceph_ino(&ci->vfs_inode), cap,
+ " (mask %s)\n", ceph_ino(&ci->netfs.inode), cap,
ceph_cap_string(cap->issued),
ceph_cap_string(mask));
if (touch)
@@ -891,7 +891,7 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
have |= cap->issued;
if ((have & mask) == mask) {
dout("__ceph_caps_issued_mask ino 0x%llx combo issued %s"
- " (mask %s)\n", ceph_ino(&ci->vfs_inode),
+ " (mask %s)\n", ceph_ino(&ci->netfs.inode),
ceph_cap_string(cap->issued),
ceph_cap_string(mask));
if (touch) {
@@ -919,7 +919,7 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
int __ceph_caps_issued_mask_metric(struct ceph_inode_info *ci, int mask,
int touch)
{
- struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+ struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
int r;
r = __ceph_caps_issued_mask(ci, mask, touch);
@@ -950,7 +950,7 @@ int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
int ceph_caps_revoking(struct ceph_inode_info *ci, int mask)
{
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
int ret;
spin_lock(&ci->i_ceph_lock);
@@ -969,8 +969,8 @@ int __ceph_caps_used(struct ceph_inode_info *ci)
if (ci->i_rd_ref)
used |= CEPH_CAP_FILE_RD;
if (ci->i_rdcache_ref ||
- (S_ISREG(ci->vfs_inode.i_mode) &&
- ci->vfs_inode.i_data.nrpages))
+ (S_ISREG(ci->netfs.inode.i_mode) &&
+ ci->netfs.inode.i_data.nrpages))
used |= CEPH_CAP_FILE_CACHE;
if (ci->i_wr_ref)
used |= CEPH_CAP_FILE_WR;
@@ -993,11 +993,11 @@ int __ceph_caps_file_wanted(struct ceph_inode_info *ci)
const int WR_SHIFT = ffs(CEPH_FILE_MODE_WR);
const int LAZY_SHIFT = ffs(CEPH_FILE_MODE_LAZY);
struct ceph_mount_options *opt =
- ceph_inode_to_client(&ci->vfs_inode)->mount_options;
+ ceph_inode_to_client(&ci->netfs.inode)->mount_options;
unsigned long used_cutoff = jiffies - opt->caps_wanted_delay_max * HZ;
unsigned long idle_cutoff = jiffies - opt->caps_wanted_delay_min * HZ;
- if (S_ISDIR(ci->vfs_inode.i_mode)) {
+ if (S_ISDIR(ci->netfs.inode.i_mode)) {
int want = 0;
/* use used_cutoff here, to keep dir's wanted caps longer */
@@ -1050,7 +1050,7 @@ int __ceph_caps_file_wanted(struct ceph_inode_info *ci)
int __ceph_caps_wanted(struct ceph_inode_info *ci)
{
int w = __ceph_caps_file_wanted(ci) | __ceph_caps_used(ci);
- if (S_ISDIR(ci->vfs_inode.i_mode)) {
+ if (S_ISDIR(ci->netfs.inode.i_mode)) {
/* we want EXCL if holding caps of dir ops */
if (w & CEPH_CAP_ANY_DIR_OPS)
w |= CEPH_CAP_FILE_EXCL;
@@ -1116,9 +1116,9 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
lockdep_assert_held(&ci->i_ceph_lock);
- dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);
+ dout("__ceph_remove_cap %p from %p\n", cap, &ci->netfs.inode);
- mdsc = ceph_inode_to_client(&ci->vfs_inode)->mdsc;
+ mdsc = ceph_inode_to_client(&ci->netfs.inode)->mdsc;
/* remove from inode's cap rbtree, and clear auth cap */
rb_erase(&cap->ci_node, &ci->i_caps);
@@ -1169,7 +1169,7 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
* keep i_snap_realm.
*/
if (ci->i_wr_ref == 0 && ci->i_snap_realm)
- ceph_change_snap_realm(&ci->vfs_inode, NULL);
+ ceph_change_snap_realm(&ci->netfs.inode, NULL);
__cap_delay_cancel(mdsc, ci);
}
@@ -1188,11 +1188,11 @@ void ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
lockdep_assert_held(&ci->i_ceph_lock);
- fsc = ceph_inode_to_client(&ci->vfs_inode);
+ fsc = ceph_inode_to_client(&ci->netfs.inode);
WARN_ON_ONCE(ci->i_auth_cap == cap &&
!list_empty(&ci->i_dirty_item) &&
!fsc->blocklisted &&
- !ceph_inode_is_shutdown(&ci->vfs_inode));
+ !ceph_inode_is_shutdown(&ci->netfs.inode));
__ceph_remove_cap(cap, queue_release);
}
@@ -1343,7 +1343,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
int flushing, u64 flush_tid, u64 oldest_flush_tid)
{
struct ceph_inode_info *ci = cap->ci;
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
int held, revoking;
lockdep_assert_held(&ci->i_ceph_lock);
@@ -1440,7 +1440,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci)
{
struct ceph_msg *msg;
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, CAP_MSG_SIZE, GFP_NOFS, false);
if (!msg) {
@@ -1528,7 +1528,7 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci,
__releases(ci->i_ceph_lock)
__acquires(ci->i_ceph_lock)
{
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
struct ceph_mds_client *mdsc = session->s_mdsc;
struct ceph_cap_snap *capsnap;
u64 oldest_flush_tid = 0;
@@ -1622,7 +1622,7 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci,
void ceph_flush_snaps(struct ceph_inode_info *ci,
struct ceph_mds_session **psession)
{
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_mds_session *session = NULL;
int mds;
@@ -1682,8 +1682,8 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
struct ceph_cap_flush **pcf)
{
struct ceph_mds_client *mdsc =
- ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
- struct inode *inode = &ci->vfs_inode;
+ ceph_sb_to_client(ci->netfs.inode.i_sb)->mdsc;
+ struct inode *inode = &ci->netfs.inode;
int was = ci->i_dirty_caps;
int dirty = 0;
@@ -1696,7 +1696,7 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
return 0;
}
- dout("__mark_dirty_caps %p %s dirty %s -> %s\n", &ci->vfs_inode,
+ dout("__mark_dirty_caps %p %s dirty %s -> %s\n", &ci->netfs.inode,
ceph_cap_string(mask), ceph_cap_string(was),
ceph_cap_string(was | mask));
ci->i_dirty_caps |= mask;
@@ -1712,7 +1712,7 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
ci->i_snap_realm->cached_context);
}
dout(" inode %p now dirty snapc %p auth cap %p\n",
- &ci->vfs_inode, ci->i_head_snapc, ci->i_auth_cap);
+ &ci->netfs.inode, ci->i_head_snapc, ci->i_auth_cap);
BUG_ON(!list_empty(&ci->i_dirty_item));
spin_lock(&mdsc->cap_dirty_lock);
list_add(&ci->i_dirty_item, &session->s_cap_dirty);
@@ -1875,7 +1875,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
bool __ceph_should_report_size(struct ceph_inode_info *ci)
{
- loff_t size = i_size_read(&ci->vfs_inode);
+ loff_t size = i_size_read(&ci->netfs.inode);
/* mds will adjust max size according to the reported size */
if (ci->i_flushing_caps & CEPH_CAP_FILE_WR)
return false;
@@ -1900,7 +1900,7 @@ bool __ceph_should_report_size(struct ceph_inode_info *ci)
void ceph_check_caps(struct ceph_inode_info *ci, int flags,
struct ceph_mds_session *session)
{
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
struct ceph_cap *cap;
u64 flush_tid, oldest_flush_tid;
@@ -2467,7 +2467,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
__releases(ci->i_ceph_lock)
__acquires(ci->i_ceph_lock)
{
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
struct ceph_cap *cap;
struct ceph_cap_flush *cf;
int ret;
@@ -2560,7 +2560,7 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
cap = ci->i_auth_cap;
if (!(cap && cap->session == session)) {
pr_err("%p auth cap %p not mds%d ???\n",
- &ci->vfs_inode, cap, session->s_mds);
+ &ci->netfs.inode, cap, session->s_mds);
spin_unlock(&ci->i_ceph_lock);
continue;
}
@@ -2610,7 +2610,7 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
cap = ci->i_auth_cap;
if (!(cap && cap->session == session)) {
pr_err("%p auth cap %p not mds%d ???\n",
- &ci->vfs_inode, cap, session->s_mds);
+ &ci->netfs.inode, cap, session->s_mds);
spin_unlock(&ci->i_ceph_lock);
continue;
}
@@ -2630,7 +2630,7 @@ void ceph_kick_flushing_inode_caps(struct ceph_mds_session *session,
lockdep_assert_held(&ci->i_ceph_lock);
- dout("%s %p flushing %s\n", __func__, &ci->vfs_inode,
+ dout("%s %p flushing %s\n", __func__, &ci->netfs.inode,
ceph_cap_string(ci->i_flushing_caps));
if (!list_empty(&ci->i_cap_flush_list)) {
@@ -2673,10 +2673,10 @@ void ceph_take_cap_refs(struct ceph_inode_info *ci, int got,
}
if (got & CEPH_CAP_FILE_BUFFER) {
if (ci->i_wb_ref == 0)
- ihold(&ci->vfs_inode);
+ ihold(&ci->netfs.inode);
ci->i_wb_ref++;
dout("%s %p wb %d -> %d (?)\n", __func__,
- &ci->vfs_inode, ci->i_wb_ref-1, ci->i_wb_ref);
+ &ci->netfs.inode, ci->i_wb_ref-1, ci->i_wb_ref);
}
}
@@ -3004,7 +3004,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
return ret;
}
- if (S_ISREG(ci->vfs_inode.i_mode) &&
+ if (S_ISREG(ci->netfs.inode.i_mode) &&
ci->i_inline_version != CEPH_INLINE_NONE &&
(_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
i_size_read(inode) > 0) {
@@ -3094,7 +3094,7 @@ enum put_cap_refs_mode {
static void __ceph_put_cap_refs(struct ceph_inode_info *ci, int had,
enum put_cap_refs_mode mode)
{
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
int last = 0, put = 0, flushsnaps = 0, wake = 0;
bool check_flushsnaps = false;
@@ -3202,7 +3202,7 @@ void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci, int had)
void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
struct ceph_snap_context *snapc)
{
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
struct ceph_cap_snap *capsnap = NULL, *iter;
int put = 0;
bool last = false;
@@ -3698,7 +3698,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
session->s_mds,
&list_first_entry(&session->s_cap_flushing,
struct ceph_inode_info,
- i_flushing_item)->vfs_inode);
+ i_flushing_item)->netfs.inode);
}
}
mdsc->num_cap_flushing--;
@@ -4345,7 +4345,7 @@ unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
break;
list_del_init(&ci->i_cap_delay_list);
- inode = igrab(&ci->vfs_inode);
+ inode = igrab(&ci->netfs.inode);
if (inode) {
spin_unlock(&mdsc->cap_delay_lock);
dout("check_delayed_caps on %p\n", inode);
@@ -4373,7 +4373,7 @@ static void flush_dirty_session_caps(struct ceph_mds_session *s)
while (!list_empty(&s->s_cap_dirty)) {
ci = list_first_entry(&s->s_cap_dirty, struct ceph_inode_info,
i_dirty_item);
- inode = &ci->vfs_inode;
+ inode = &ci->netfs.inode;
ihold(inode);
dout("flush_dirty_caps %llx.%llx\n", ceph_vinop(inode));
spin_unlock(&mdsc->cap_dirty_lock);
@@ -4407,7 +4407,7 @@ void __ceph_touch_fmode(struct ceph_inode_info *ci,
void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
{
- struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->vfs_inode.i_sb);
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->netfs.inode.i_sb);
int bits = (fmode << 1) | 1;
bool already_opened = false;
int i;
@@ -4441,7 +4441,7 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
*/
void ceph_put_fmode(struct ceph_inode_info *ci, int fmode, int count)
{
- struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->vfs_inode.i_sb);
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->netfs.inode.i_sb);
int bits = (fmode << 1) | 1;
bool is_closed = true;
int i;
@@ -4656,7 +4656,7 @@ int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invali
lockdep_assert_held(&ci->i_ceph_lock);
dout("removing cap %p, ci is %p, inode is %p\n",
- cap, ci, &ci->vfs_inode);
+ cap, ci, &ci->netfs.inode);
is_auth = (cap == ci->i_auth_cap);
__ceph_remove_cap(cap, false);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 8c8226c0feac..da59e836a06e 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -205,7 +205,7 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mount_options *opt =
- ceph_inode_to_client(&ci->vfs_inode)->mount_options;
+ ceph_inode_to_client(&ci->netfs.inode)->mount_options;
struct ceph_file_info *fi;
int ret;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 5f1cc2b4ed06..650746b3ba99 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -20,9 +20,6 @@
#include "cache.h"
#include <linux/ceph/decode.h>
-// Temporary: netfs does disgusting things with inode pointers
-#pragma GCC diagnostic ignored "-Wattribute-warning"
-
/*
* Ceph inode operations
*
@@ -179,7 +176,7 @@ static struct ceph_inode_frag *__get_or_create_frag(struct ceph_inode_info *ci,
rb_insert_color(&frag->node, &ci->i_fragtree);
dout("get_or_create_frag added %llx.%llx frag %x\n",
- ceph_vinop(&ci->vfs_inode), f);
+ ceph_vinop(&ci->netfs.inode), f);
return frag;
}
@@ -460,10 +457,10 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
if (!ci)
return NULL;
- dout("alloc_inode %p\n", &ci->vfs_inode);
+ dout("alloc_inode %p\n", &ci->netfs.inode);
/* Set parameters for the netfs library */
- netfs_i_context_init(&ci->vfs_inode, &ceph_netfs_ops);
+ netfs_inode_init(&ci->netfs.inode, &ceph_netfs_ops);
spin_lock_init(&ci->i_ceph_lock);
@@ -550,7 +547,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
INIT_WORK(&ci->i_work, ceph_inode_work);
ci->i_work_mask = 0;
memset(&ci->i_btime, '\0', sizeof(ci->i_btime));
- return &ci->vfs_inode;
+ return &ci->netfs.inode;
}
void ceph_free_inode(struct inode *inode)
@@ -1981,7 +1978,7 @@ static void ceph_inode_work(struct work_struct *work)
{
struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
i_work);
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
if (test_and_clear_bit(CEPH_I_WORK_WRITEBACK, &ci->i_work_mask)) {
dout("writeback %p\n", inode);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f5d110d90b77..33f517d549ce 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1564,7 +1564,7 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session,
p = session->s_caps.next;
while (p != &session->s_caps) {
cap = list_entry(p, struct ceph_cap, session_caps);
- inode = igrab(&cap->ci->vfs_inode);
+ inode = igrab(&cap->ci->netfs.inode);
if (!inode) {
p = p->next;
continue;
@@ -1622,7 +1622,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
int iputs;
dout("removing cap %p, ci is %p, inode is %p\n",
- cap, ci, &ci->vfs_inode);
+ cap, ci, &ci->netfs.inode);
spin_lock(&ci->i_ceph_lock);
iputs = ceph_purge_inode_cap(inode, cap, &invalidate);
spin_unlock(&ci->i_ceph_lock);
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 322ee5add942..864cdaa0d2bd 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -521,7 +521,7 @@ static bool has_new_snaps(struct ceph_snap_context *o,
static void ceph_queue_cap_snap(struct ceph_inode_info *ci,
struct ceph_cap_snap **pcapsnap)
{
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
struct ceph_snap_context *old_snapc, *new_snapc;
struct ceph_cap_snap *capsnap = *pcapsnap;
struct ceph_buffer *old_blob = NULL;
@@ -652,7 +652,7 @@ update_snapc:
int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
struct ceph_cap_snap *capsnap)
{
- struct inode *inode = &ci->vfs_inode;
+ struct inode *inode = &ci->netfs.inode;
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
BUG_ON(capsnap->writing);
@@ -712,7 +712,7 @@ static void queue_realm_cap_snaps(struct ceph_snap_realm *realm)
spin_lock(&realm->inodes_with_caps_lock);
list_for_each_entry(ci, &realm->inodes_with_caps, i_snap_realm_item) {
- struct inode *inode = igrab(&ci->vfs_inode);
+ struct inode *inode = igrab(&ci->netfs.inode);
if (!inode)
continue;
spin_unlock(&realm->inodes_with_caps_lock);
@@ -904,7 +904,7 @@ static void flush_snaps(struct ceph_mds_client *mdsc)
while (!list_empty(&mdsc->snap_flush_list)) {
ci = list_first_entry(&mdsc->snap_flush_list,
struct ceph_inode_info, i_snap_flush_item);
- inode = &ci->vfs_inode;
+ inode = &ci->netfs.inode;
ihold(inode);
spin_unlock(&mdsc->snap_flush_lock);
ceph_flush_snaps(ci, &session);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index b73b4f75462c..40140805bdcf 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -876,7 +876,7 @@ mempool_t *ceph_wb_pagevec_pool;
static void ceph_inode_init_once(void *foo)
{
struct ceph_inode_info *ci = foo;
- inode_init_once(&ci->vfs_inode);
+ inode_init_once(&ci->netfs.inode);
}
static int __init init_caches(void)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index dd7dac0f984a..f59dac66955b 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -316,11 +316,7 @@ struct ceph_inode_xattrs_info {
* Ceph inode.
*/
struct ceph_inode_info {
- struct {
- /* These must be contiguous */
- struct inode vfs_inode;
- struct netfs_i_context netfs_ctx; /* Netfslib context */
- };
+ struct netfs_inode netfs; /* Netfslib context and vfs inode */
struct ceph_vino i_vino; /* ceph ino + snap */
spinlock_t i_ceph_lock;
@@ -436,7 +432,7 @@ struct ceph_inode_info {
static inline struct ceph_inode_info *
ceph_inode(const struct inode *inode)
{
- return container_of(inode, struct ceph_inode_info, vfs_inode);
+ return container_of(inode, struct ceph_inode_info, netfs.inode);
}
static inline struct ceph_fs_client *
@@ -1316,7 +1312,7 @@ static inline void __ceph_update_quota(struct ceph_inode_info *ci,
has_quota = __ceph_has_quota(ci, QUOTA_GET_ANY);
if (had_quota != has_quota)
- ceph_adjust_quota_realms_count(&ci->vfs_inode, has_quota);
+ ceph_adjust_quota_realms_count(&ci->netfs.inode, has_quota);
}
extern void ceph_handle_quota(struct ceph_mds_client *mdsc,
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 8c2dc2c762a4..f141f5246163 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -57,7 +57,7 @@ static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci)
static ssize_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
size_t size)
{
- struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+ struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
struct ceph_osd_client *osdc = &fsc->client->osdc;
struct ceph_string *pool_ns;
s64 pool = ci->i_layout.pool_id;
@@ -69,7 +69,7 @@ static ssize_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
- dout("ceph_vxattrcb_layout %p\n", &ci->vfs_inode);
+ dout("ceph_vxattrcb_layout %p\n", &ci->netfs.inode);
down_read(&osdc->lock);
pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
if (pool_name) {
@@ -161,7 +161,7 @@ static ssize_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
char *val, size_t size)
{
ssize_t ret;
- struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+ struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
struct ceph_osd_client *osdc = &fsc->client->osdc;
s64 pool = ci->i_layout.pool_id;
const char *pool_name;
@@ -313,7 +313,7 @@ static ssize_t ceph_vxattrcb_snap_btime(struct ceph_inode_info *ci, char *val,
static ssize_t ceph_vxattrcb_cluster_fsid(struct ceph_inode_info *ci,
char *val, size_t size)
{
- struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+ struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
return ceph_fmt_xattr(val, size, "%pU", &fsc->client->fsid);
}
@@ -321,7 +321,7 @@ static ssize_t ceph_vxattrcb_cluster_fsid(struct ceph_inode_info *ci,
static ssize_t ceph_vxattrcb_client_id(struct ceph_inode_info *ci,
char *val, size_t size)
{
- struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+ struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
return ceph_fmt_xattr(val, size, "client%lld",
ceph_client_gid(fsc->client));
@@ -629,7 +629,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
}
dout("__set_xattr_val added %llx.%llx xattr %p %.*s=%.*s\n",
- ceph_vinop(&ci->vfs_inode), xattr, name_len, name, val_len, val);
+ ceph_vinop(&ci->netfs.inode), xattr, name_len, name, val_len, val);
return 0;
}
@@ -871,7 +871,7 @@ struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci)
struct ceph_buffer *old_blob = NULL;
void *dest;
- dout("__build_xattrs_blob %p\n", &ci->vfs_inode);
+ dout("__build_xattrs_blob %p\n", &ci->netfs.inode);
if (ci->i_xattrs.dirty) {
int need = __get_required_blob_size(ci, 0, 0);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 12c872800326..c85d9a378325 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -377,7 +377,7 @@ cifs_alloc_inode(struct super_block *sb)
cifs_inode->flags = 0;
spin_lock_init(&cifs_inode->writers_lock);
cifs_inode->writers = 0;
- cifs_inode->vfs_inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */
+ cifs_inode->netfs.inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */
cifs_inode->server_eof = 0;
cifs_inode->uniqueid = 0;
cifs_inode->createtime = 0;
@@ -389,12 +389,12 @@ cifs_alloc_inode(struct super_block *sb)
* Can not set i_flags here - they get immediately overwritten to zero
* by the VFS.
*/
- /* cifs_inode->vfs_inode.i_flags = S_NOATIME | S_NOCMTIME; */
+ /* cifs_inode->netfs.inode.i_flags = S_NOATIME | S_NOCMTIME; */
INIT_LIST_HEAD(&cifs_inode->openFileList);
INIT_LIST_HEAD(&cifs_inode->llist);
INIT_LIST_HEAD(&cifs_inode->deferred_closes);
spin_lock_init(&cifs_inode->deferred_lock);
- return &cifs_inode->vfs_inode;
+ return &cifs_inode->netfs.inode;
}
static void
@@ -1418,7 +1418,7 @@ cifs_init_once(void *inode)
{
struct cifsInodeInfo *cifsi = inode;
- inode_init_once(&cifsi->vfs_inode);
+ inode_init_once(&cifsi->netfs.inode);
init_rwsem(&cifsi->lock_sem);
}
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index f873379066c7..e7737166e5b8 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1479,20 +1479,16 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
#define CIFS_CACHE_RW_FLG (CIFS_CACHE_READ_FLG | CIFS_CACHE_WRITE_FLG)
#define CIFS_CACHE_RHW_FLG (CIFS_CACHE_RW_FLG | CIFS_CACHE_HANDLE_FLG)
-#define CIFS_CACHE_READ(cinode) ((cinode->oplock & CIFS_CACHE_READ_FLG) || (CIFS_SB(cinode->vfs_inode.i_sb)->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE))
+#define CIFS_CACHE_READ(cinode) ((cinode->oplock & CIFS_CACHE_READ_FLG) || (CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE))
#define CIFS_CACHE_HANDLE(cinode) (cinode->oplock & CIFS_CACHE_HANDLE_FLG)
-#define CIFS_CACHE_WRITE(cinode) ((cinode->oplock & CIFS_CACHE_WRITE_FLG) || (CIFS_SB(cinode->vfs_inode.i_sb)->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE))
+#define CIFS_CACHE_WRITE(cinode) ((cinode->oplock & CIFS_CACHE_WRITE_FLG) || (CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE))
/*
* One of these for each file inode
*/
struct cifsInodeInfo {
- struct {
- /* These must be contiguous */
- struct inode vfs_inode; /* the VFS's inode record */
- struct netfs_i_context netfs_ctx; /* Netfslib context */
- };
+ struct netfs_inode netfs; /* Netfslib context and vfs inode */
bool can_cache_brlcks;
struct list_head llist; /* locks helb by this inode */
/*
@@ -1531,7 +1527,7 @@ struct cifsInodeInfo {
static inline struct cifsInodeInfo *
CIFS_I(struct inode *inode)
{
- return container_of(inode, struct cifsInodeInfo, vfs_inode);
+ return container_of(inode, struct cifsInodeInfo, netfs.inode);
}
static inline struct cifs_sb_info *
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 1618e0537d58..e64cda7a7610 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2004,7 +2004,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
bool fsuid_only)
{
struct cifsFileInfo *open_file = NULL;
- struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);
+ struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb);
/* only filter by fsuid on multiuser mounts */
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
@@ -2060,7 +2060,7 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags,
return rc;
}
- cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);
+ cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb);
/* only filter by fsuid on multiuser mounts */
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
@@ -4669,14 +4669,14 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file)
/* This inode is open for write at least once */
struct cifs_sb_info *cifs_sb;
- cifs_sb = CIFS_SB(cifsInode->vfs_inode.i_sb);
+ cifs_sb = CIFS_SB(cifsInode->netfs.inode.i_sb);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) {
/* since no page cache to corrupt on directio
we can change size safely */
return true;
}
- if (i_size_read(&cifsInode->vfs_inode) < end_of_file)
+ if (i_size_read(&cifsInode->netfs.inode) < end_of_file)
return true;
return false;
diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c
index a638b29e9062..23ef56f55ce5 100644
--- a/fs/cifs/fscache.c
+++ b/fs/cifs/fscache.c
@@ -101,13 +101,13 @@ void cifs_fscache_get_inode_cookie(struct inode *inode)
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
- cifs_fscache_fill_coherency(&cifsi->vfs_inode, &cd);
+ cifs_fscache_fill_coherency(&cifsi->netfs.inode, &cd);
- cifsi->netfs_ctx.cache =
+ cifsi->netfs.cache =
fscache_acquire_cookie(tcon->fscache, 0,
&cifsi->uniqueid, sizeof(cifsi->uniqueid),
&cd, sizeof(cd),
- i_size_read(&cifsi->vfs_inode));
+ i_size_read(&cifsi->netfs.inode));
}
void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update)
@@ -131,7 +131,7 @@ void cifs_fscache_release_inode_cookie(struct inode *inode)
if (cookie) {
cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cookie);
fscache_relinquish_cookie(cookie, false);
- cifsi->netfs_ctx.cache = NULL;
+ cifsi->netfs.cache = NULL;
}
}
diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h
index 52355c0912ae..ab9a51d0125c 100644
--- a/fs/cifs/fscache.h
+++ b/fs/cifs/fscache.h
@@ -52,10 +52,10 @@ void cifs_fscache_fill_coherency(struct inode *inode,
struct cifsInodeInfo *cifsi = CIFS_I(inode);
memset(cd, 0, sizeof(*cd));
- cd->last_write_time_sec = cpu_to_le64(cifsi->vfs_inode.i_mtime.tv_sec);
- cd->last_write_time_nsec = cpu_to_le32(cifsi->vfs_inode.i_mtime.tv_nsec);
- cd->last_change_time_sec = cpu_to_le64(cifsi->vfs_inode.i_ctime.tv_sec);
- cd->last_change_time_nsec = cpu_to_le32(cifsi->vfs_inode.i_ctime.tv_nsec);
+ cd->last_write_time_sec = cpu_to_le64(cifsi->netfs.inode.i_mtime.tv_sec);
+ cd->last_write_time_nsec = cpu_to_le32(cifsi->netfs.inode.i_mtime.tv_nsec);
+ cd->last_change_time_sec = cpu_to_le64(cifsi->netfs.inode.i_ctime.tv_sec);
+ cd->last_change_time_nsec = cpu_to_le32(cifsi->netfs.inode.i_ctime.tv_nsec);
}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 2f9e7d2f81b6..81da81e18553 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -115,7 +115,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
__func__, cifs_i->uniqueid);
set_bit(CIFS_INO_INVALID_MAPPING, &cifs_i->flags);
/* Invalidate fscache cookie */
- cifs_fscache_fill_coherency(&cifs_i->vfs_inode, &cd);
+ cifs_fscache_fill_coherency(&cifs_i->netfs.inode, &cd);
fscache_invalidate(cifs_inode_cookie(inode), &cd, i_size_read(inode), 0);
}
@@ -2499,7 +2499,7 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start,
u64 len)
{
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
- struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_i->vfs_inode.i_sb);
+ struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_i->netfs.inode.i_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
struct TCP_Server_Info *server = tcon->ses->server;
struct cifsFileInfo *cfile;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 35962a1a23b9..cbc3b433f502 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -537,11 +537,11 @@ void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock)
if (oplock == OPLOCK_EXCLUSIVE) {
cinode->oplock = CIFS_CACHE_WRITE_FLG | CIFS_CACHE_READ_FLG;
cifs_dbg(FYI, "Exclusive Oplock granted on inode %p\n",
- &cinode->vfs_inode);
+ &cinode->netfs.inode);
} else if (oplock == OPLOCK_READ) {
cinode->oplock = CIFS_CACHE_READ_FLG;
cifs_dbg(FYI, "Level II Oplock granted on inode %p\n",
- &cinode->vfs_inode);
+ &cinode->netfs.inode);
} else
cinode->oplock = 0;
}
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 98a76fa791c0..8543cafdfd34 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -4260,15 +4260,15 @@ smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
if (oplock == SMB2_OPLOCK_LEVEL_BATCH) {
cinode->oplock = CIFS_CACHE_RHW_FLG;
cifs_dbg(FYI, "Batch Oplock granted on inode %p\n",
- &cinode->vfs_inode);
+ &cinode->netfs.inode);
} else if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE) {
cinode->oplock = CIFS_CACHE_RW_FLG;
cifs_dbg(FYI, "Exclusive Oplock granted on inode %p\n",
- &cinode->vfs_inode);
+ &cinode->netfs.inode);
} else if (oplock == SMB2_OPLOCK_LEVEL_II) {
cinode->oplock = CIFS_CACHE_READ_FLG;
cifs_dbg(FYI, "Level II Oplock granted on inode %p\n",
- &cinode->vfs_inode);
+ &cinode->netfs.inode);
} else
cinode->oplock = 0;
}
@@ -4307,7 +4307,7 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
cinode->oplock = new_oplock;
cifs_dbg(FYI, "%s Lease granted on inode %p\n", message,
- &cinode->vfs_inode);
+ &cinode->netfs.inode);
}
static void
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 360ce3604a2d..e6b932219803 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1549,7 +1549,7 @@ static int __ext2_write_inode(struct inode *inode, int do_sync)
if (IS_ERR(raw_inode))
return -EIO;
- /* For fields not not tracking in the in-memory inode,
+ /* For fields not tracking in the in-memory inode,
* initialise them to zero for new inodes. */
if (ei->i_state & EXT2_STATE_NEW)
memset(raw_inode, 0, EXT2_SB(sb)->s_inode_size);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index a21d8f1a56d1..05221366a16d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -120,6 +120,7 @@ static bool inode_io_list_move_locked(struct inode *inode,
struct list_head *head)
{
assert_spin_locked(&wb->list_lock);
+ assert_spin_locked(&inode->i_lock);
list_move(&inode->i_io_list, head);
@@ -1365,9 +1366,9 @@ static int move_expired_inodes(struct list_head *delaying_queue,
inode = wb_inode(delaying_queue->prev);
if (inode_dirtied_after(inode, dirtied_before))
break;
+ spin_lock(&inode->i_lock);
list_move(&inode->i_io_list, &tmp);
moved++;
- spin_lock(&inode->i_lock);
inode->i_state |= I_SYNC_QUEUED;
spin_unlock(&inode->i_lock);
if (sb_is_blkdev_sb(inode->i_sb))
@@ -1383,7 +1384,12 @@ static int move_expired_inodes(struct list_head *delaying_queue,
goto out;
}
- /* Move inodes from one superblock together */
+ /*
+ * Although inode's i_io_list is moved from 'tmp' to 'dispatch_queue',
+ * we don't take inode->i_lock here because it is just a pointless overhead.
+ * Inode is already marked as I_SYNC_QUEUED so writeback list handling is
+ * fully under our control.
+ */
while (!list_empty(&tmp)) {
sb = wb_inode(tmp.prev)->i_sb;
list_for_each_prev_safe(pos, node, &tmp) {
@@ -1826,8 +1832,8 @@ static long writeback_sb_inodes(struct super_block *sb,
* We'll have another go at writing back this inode
* when we completed a full scan of b_io.
*/
- spin_unlock(&inode->i_lock);
requeue_io(inode, wb);
+ spin_unlock(&inode->i_lock);
trace_writeback_sb_inodes_requeue(inode);
continue;
}
@@ -2358,6 +2364,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
{
struct super_block *sb = inode->i_sb;
int dirtytime = 0;
+ struct bdi_writeback *wb = NULL;
trace_writeback_mark_inode_dirty(inode, flags);
@@ -2410,13 +2417,24 @@ void __mark_inode_dirty(struct inode *inode, int flags)
inode->i_state |= flags;
/*
+ * Grab inode's wb early because it requires dropping i_lock and we
+ * need to make sure following checks happen atomically with dirty
+ * list handling so that we don't move inodes under flush worker's
+ * hands.
+ */
+ if (!was_dirty) {
+ wb = locked_inode_to_wb_and_lock_list(inode);
+ spin_lock(&inode->i_lock);
+ }
+
+ /*
* If the inode is queued for writeback by flush worker, just
* update its dirty state. Once the flush worker is done with
* the inode it will place it on the appropriate superblock
* list, based upon its state.
*/
if (inode->i_state & I_SYNC_QUEUED)
- goto out_unlock_inode;
+ goto out_unlock;
/*
* Only add valid (hashed) inodes to the superblock's
@@ -2424,22 +2442,19 @@ void __mark_inode_dirty(struct inode *inode, int flags)
*/
if (!S_ISBLK(inode->i_mode)) {
if (inode_unhashed(inode))
- goto out_unlock_inode;
+ goto out_unlock;
}
if (inode->i_state & I_FREEING)
- goto out_unlock_inode;
+ goto out_unlock;
/*
* If the inode was already on b_dirty/b_io/b_more_io, don't
* reposition it (that would break b_dirty time-ordering).
*/
if (!was_dirty) {
- struct bdi_writeback *wb;
struct list_head *dirty_list;
bool wakeup_bdi = false;
- wb = locked_inode_to_wb_and_lock_list(inode);
-
inode->dirtied_when = jiffies;
if (dirtytime)
inode->dirtied_time_when = jiffies;
@@ -2453,6 +2468,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
dirty_list);
spin_unlock(&wb->list_lock);
+ spin_unlock(&inode->i_lock);
trace_writeback_dirty_inode_enqueue(inode);
/*
@@ -2467,6 +2483,9 @@ void __mark_inode_dirty(struct inode *inode, int flags)
return;
}
}
+out_unlock:
+ if (wb)
+ spin_unlock(&wb->list_lock);
out_unlock_inode:
spin_unlock(&inode->i_lock);
}
diff --git a/fs/inode.c b/fs/inode.c
index 9d9b422504d1..bd4da9c5207e 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -27,7 +27,7 @@
* Inode locking rules:
*
* inode->i_lock protects:
- * inode->i_state, inode->i_hash, __iget()
+ * inode->i_state, inode->i_hash, __iget(), inode->i_io_list
* Inode LRU list locks protect:
* inode->i_sb->s_inode_lru, inode->i_lru
* inode->i_sb->s_inode_list_lock protects:
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 8742d22dfd2b..d37e012386f3 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -155,7 +155,7 @@ static void netfs_rreq_expand(struct netfs_io_request *rreq,
void netfs_readahead(struct readahead_control *ractl)
{
struct netfs_io_request *rreq;
- struct netfs_i_context *ctx = netfs_i_context(ractl->mapping->host);
+ struct netfs_inode *ctx = netfs_inode(ractl->mapping->host);
int ret;
_enter("%lx,%x", readahead_index(ractl), readahead_count(ractl));
@@ -215,7 +215,7 @@ int netfs_read_folio(struct file *file, struct folio *folio)
{
struct address_space *mapping = folio_file_mapping(folio);
struct netfs_io_request *rreq;
- struct netfs_i_context *ctx = netfs_i_context(mapping->host);
+ struct netfs_inode *ctx = netfs_inode(mapping->host);
int ret;
_enter("%lx", folio_index(folio));
@@ -331,7 +331,7 @@ int netfs_write_begin(struct file *file, struct address_space *mapping,
void **_fsdata)
{
struct netfs_io_request *rreq;
- struct netfs_i_context *ctx = netfs_i_context(file_inode(file ));
+ struct netfs_inode *ctx = netfs_inode(file_inode(file ));
struct folio *folio;
unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
pgoff_t index = pos >> PAGE_SHIFT;
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index b7b0e3d18d9e..43fac1b14e40 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -91,7 +91,7 @@ static inline void netfs_stat_d(atomic_t *stat)
/*
* Miscellaneous functions.
*/
-static inline bool netfs_is_cache_enabled(struct netfs_i_context *ctx)
+static inline bool netfs_is_cache_enabled(struct netfs_inode *ctx)
{
#if IS_ENABLED(CONFIG_FSCACHE)
struct fscache_cookie *cookie = ctx->cache;
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index e86107b30ba4..c6afa605b63b 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -18,7 +18,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
{
static atomic_t debug_ids;
struct inode *inode = file ? file_inode(file) : mapping->host;
- struct netfs_i_context *ctx = netfs_i_context(inode);
+ struct netfs_inode *ctx = netfs_inode(inode);
struct netfs_io_request *rreq;
int ret;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index a74aef99bd3d..09d1307959d0 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -79,6 +79,7 @@
#include <linux/capability.h>
#include <linux/quotaops.h>
#include <linux/blkdev.h>
+#include <linux/sched/mm.h>
#include "../internal.h" /* ugh */
#include <linux/uaccess.h>
@@ -425,9 +426,11 @@ EXPORT_SYMBOL(mark_info_dirty);
int dquot_acquire(struct dquot *dquot)
{
int ret = 0, ret2 = 0;
+ unsigned int memalloc;
struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
mutex_lock(&dquot->dq_lock);
+ memalloc = memalloc_nofs_save();
if (!test_bit(DQ_READ_B, &dquot->dq_flags)) {
ret = dqopt->ops[dquot->dq_id.type]->read_dqblk(dquot);
if (ret < 0)
@@ -458,6 +461,7 @@ int dquot_acquire(struct dquot *dquot)
smp_mb__before_atomic();
set_bit(DQ_ACTIVE_B, &dquot->dq_flags);
out_iolock:
+ memalloc_nofs_restore(memalloc);
mutex_unlock(&dquot->dq_lock);
return ret;
}
@@ -469,9 +473,11 @@ EXPORT_SYMBOL(dquot_acquire);
int dquot_commit(struct dquot *dquot)
{
int ret = 0;
+ unsigned int memalloc;
struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
mutex_lock(&dquot->dq_lock);
+ memalloc = memalloc_nofs_save();
if (!clear_dquot_dirty(dquot))
goto out_lock;
/* Inactive dquot can be only if there was error during read/init
@@ -481,6 +487,7 @@ int dquot_commit(struct dquot *dquot)
else
ret = -EIO;
out_lock:
+ memalloc_nofs_restore(memalloc);
mutex_unlock(&dquot->dq_lock);
return ret;
}
@@ -492,9 +499,11 @@ EXPORT_SYMBOL(dquot_commit);
int dquot_release(struct dquot *dquot)
{
int ret = 0, ret2 = 0;
+ unsigned int memalloc;
struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
mutex_lock(&dquot->dq_lock);
+ memalloc = memalloc_nofs_save();
/* Check whether we are not racing with some other dqget() */
if (dquot_is_busy(dquot))
goto out_dqlock;
@@ -510,6 +519,7 @@ int dquot_release(struct dquot *dquot)
}
clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
out_dqlock:
+ memalloc_nofs_restore(memalloc);
mutex_unlock(&dquot->dq_lock);
return ret;
}
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 302506bbc2a4..8e47d483b524 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -44,6 +44,7 @@ mandatory-y += msi.h
mandatory-y += pci.h
mandatory-y += percpu.h
mandatory-y += pgalloc.h
+mandatory-y += platform-feature.h
mandatory-y += preempt.h
mandatory-y += rwonce.h
mandatory-y += sections.h
diff --git a/include/asm-generic/platform-feature.h b/include/asm-generic/platform-feature.h
new file mode 100644
index 000000000000..4b0af3d51588
--- /dev/null
+++ b/include/asm-generic/platform-feature.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_PLATFORM_FEATURE_H
+#define _ASM_GENERIC_PLATFORM_FEATURE_H
+
+/* Number of arch specific feature flags. */
+#define PLATFORM_ARCH_FEAT_N 0
+
+#endif /* _ASM_GENERIC_PLATFORM_FEATURE_H */
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 77fa6a61706a..6dbb4c9ce50d 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -119,9 +119,10 @@ typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error,
bool was_async);
/*
- * Per-inode description. This must be directly after the inode struct.
+ * Per-inode context. This wraps the VFS inode.
*/
-struct netfs_i_context {
+struct netfs_inode {
+ struct inode inode; /* The VFS inode */
const struct netfs_request_ops *ops;
#if IS_ENABLED(CONFIG_FSCACHE)
struct fscache_cookie *cache;
@@ -256,7 +257,7 @@ struct netfs_cache_ops {
* boundary as appropriate.
*/
enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq,
- loff_t i_size);
+ loff_t i_size);
/* Prepare a write operation, working out what part of the write we can
* actually do.
@@ -288,45 +289,35 @@ extern void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
extern void netfs_stats_show(struct seq_file *);
/**
- * netfs_i_context - Get the netfs inode context from the inode
+ * netfs_inode - Get the netfs inode context from the inode
* @inode: The inode to query
*
* Get the netfs lib inode context from the network filesystem's inode. The
* context struct is expected to directly follow on from the VFS inode struct.
*/
-static inline struct netfs_i_context *netfs_i_context(struct inode *inode)
+static inline struct netfs_inode *netfs_inode(struct inode *inode)
{
- return (void *)inode + sizeof(*inode);
+ return container_of(inode, struct netfs_inode, inode);
}
/**
- * netfs_inode - Get the netfs inode from the inode context
- * @ctx: The context to query
- *
- * Get the netfs inode from the netfs library's inode context. The VFS inode
- * is expected to directly precede the context struct.
- */
-static inline struct inode *netfs_inode(struct netfs_i_context *ctx)
-{
- return (void *)ctx - sizeof(struct inode);
-}
-
-/**
- * netfs_i_context_init - Initialise a netfs lib context
+ * netfs_inode_init - Initialise a netfslib inode context
* @inode: The inode with which the context is associated
* @ops: The netfs's operations list
*
* Initialise the netfs library context struct. This is expected to follow on
* directly from the VFS inode struct.
*/
-static inline void netfs_i_context_init(struct inode *inode,
- const struct netfs_request_ops *ops)
+static inline void netfs_inode_init(struct inode *inode,
+ const struct netfs_request_ops *ops)
{
- struct netfs_i_context *ctx = netfs_i_context(inode);
+ struct netfs_inode *ctx = netfs_inode(inode);
- memset(ctx, 0, sizeof(*ctx));
ctx->ops = ops;
ctx->remote_i_size = i_size_read(inode);
+#if IS_ENABLED(CONFIG_FSCACHE)
+ ctx->cache = NULL;
+#endif
}
/**
@@ -338,7 +329,7 @@ static inline void netfs_i_context_init(struct inode *inode,
*/
static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size)
{
- struct netfs_i_context *ctx = netfs_i_context(inode);
+ struct netfs_inode *ctx = netfs_inode(inode);
ctx->remote_i_size = new_i_size;
}
@@ -352,7 +343,7 @@ static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size)
static inline struct fscache_cookie *netfs_i_cookie(struct inode *inode)
{
#if IS_ENABLED(CONFIG_FSCACHE)
- struct netfs_i_context *ctx = netfs_i_context(inode);
+ struct netfs_inode *ctx = netfs_inode(inode);
return ctx->cache;
#else
return NULL;
diff --git a/include/linux/platform-feature.h b/include/linux/platform-feature.h
new file mode 100644
index 000000000000..b2f48be999fa
--- /dev/null
+++ b/include/linux/platform-feature.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PLATFORM_FEATURE_H
+#define _PLATFORM_FEATURE_H
+
+#include <linux/bitops.h>
+#include <asm/platform-feature.h>
+
+/* The platform features are starting with the architecture specific ones. */
+
+/* Used to enable platform specific DMA handling for virtio devices. */
+#define PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS (0 + PLATFORM_ARCH_FEAT_N)
+
+#define PLATFORM_FEAT_N (1 + PLATFORM_ARCH_FEAT_N)
+
+void platform_set(unsigned int feature);
+void platform_clear(unsigned int feature);
+bool platform_has(unsigned int feature);
+
+#endif /* _PLATFORM_FEATURE_H */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 9a36051ceb76..49c7c32815f1 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -604,13 +604,4 @@ static inline void virtio_cwrite64(struct virtio_device *vdev,
_r; \
})
-#ifdef CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
-int arch_has_restricted_virtio_memory_access(void);
-#else
-static inline int arch_has_restricted_virtio_memory_access(void)
-{
- return 0;
-}
-#endif /* CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS */
-
#endif /* _LINUX_VIRTIO_CONFIG_H */
diff --git a/include/xen/arm/xen-ops.h b/include/xen/arm/xen-ops.h
new file mode 100644
index 000000000000..b0766a660338
--- /dev/null
+++ b/include/xen/arm/xen-ops.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM_XEN_OPS_H
+#define _ASM_ARM_XEN_OPS_H
+
+#include <xen/swiotlb-xen.h>
+#include <xen/xen-ops.h>
+
+static inline void xen_setup_dma_ops(struct device *dev)
+{
+#ifdef CONFIG_XEN
+ if (xen_is_grant_dma_device(dev))
+ xen_grant_setup_dma_ops(dev);
+ else if (xen_swiotlb_detect())
+ dev->dma_ops = &xen_swiotlb_dma_ops;
+#endif
+}
+
+#endif /* _ASM_ARM_XEN_OPS_H */
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index 527c9907f99c..e279be353e3f 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -127,10 +127,14 @@ int gnttab_try_end_foreign_access(grant_ref_t ref);
*/
int gnttab_alloc_grant_references(u16 count, grant_ref_t *pprivate_head);
+int gnttab_alloc_grant_reference_seq(unsigned int count, grant_ref_t *first);
+
void gnttab_free_grant_reference(grant_ref_t ref);
void gnttab_free_grant_references(grant_ref_t head);
+void gnttab_free_grant_reference_seq(grant_ref_t head, unsigned int count);
+
int gnttab_empty_grant_references(const grant_ref_t *pprivate_head);
int gnttab_claim_grant_reference(grant_ref_t *pprivate_head);
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index c7c1b46ff4cd..80546960f8b7 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -214,4 +214,17 @@ static inline void xen_preemptible_hcall_end(void) { }
#endif /* CONFIG_XEN_PV && !CONFIG_PREEMPTION */
+#ifdef CONFIG_XEN_GRANT_DMA_OPS
+void xen_grant_setup_dma_ops(struct device *dev);
+bool xen_is_grant_dma_device(struct device *dev);
+#else
+static inline void xen_grant_setup_dma_ops(struct device *dev)
+{
+}
+static inline bool xen_is_grant_dma_device(struct device *dev)
+{
+ return false;
+}
+#endif /* CONFIG_XEN_GRANT_DMA_OPS */
+
#endif /* INCLUDE_XEN_OPS_H */
diff --git a/include/xen/xen.h b/include/xen/xen.h
index a99bab817523..0780a81e140d 100644
--- a/include/xen/xen.h
+++ b/include/xen/xen.h
@@ -52,6 +52,14 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
extern u64 xen_saved_max_mem_size;
#endif
+#include <linux/platform-feature.h>
+
+static inline void xen_set_restricted_virtio_memory_access(void)
+{
+ if (IS_ENABLED(CONFIG_XEN_VIRTIO) && xen_domain())
+ platform_set(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS);
+}
+
#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages);
void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages);
diff --git a/kernel/Makefile b/kernel/Makefile
index 318789c728d3..a7e1f49ab2b3 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -7,7 +7,7 @@ obj-y = fork.o exec_domain.o panic.o \
cpu.o exit.o softirq.o resource.o \
sysctl.o capability.o ptrace.o user.o \
signal.o sys.o umh.o workqueue.o pid.o task_work.o \
- extable.o params.o \
+ extable.o params.o platform-feature.o \
kthread.o sys_ni.o nsproxy.o \
notifier.o ksysfs.o cred.o reboot.o \
async.o range.o smpboot.o ucount.o regset.o
diff --git a/kernel/platform-feature.c b/kernel/platform-feature.c
new file mode 100644
index 000000000000..cb6a6c3e4fed
--- /dev/null
+++ b/kernel/platform-feature.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bitops.h>
+#include <linux/cache.h>
+#include <linux/export.h>
+#include <linux/platform-feature.h>
+
+#define PLATFORM_FEAT_ARRAY_SZ BITS_TO_LONGS(PLATFORM_FEAT_N)
+static unsigned long __read_mostly platform_features[PLATFORM_FEAT_ARRAY_SZ];
+
+void platform_set(unsigned int feature)
+{
+ set_bit(feature, platform_features);
+}
+EXPORT_SYMBOL_GPL(platform_set);
+
+void platform_clear(unsigned int feature)
+{
+ clear_bit(feature, platform_features);
+}
+EXPORT_SYMBOL_GPL(platform_clear);
+
+bool platform_has(unsigned int feature)
+{
+ return test_bit(feature, platform_features);
+}
+EXPORT_SYMBOL_GPL(platform_has);