qemu/hw/mem/nvdimm.c

267 lines
8.0 KiB
C
Raw Normal View History

/*
* Non-Volatile Dual In-line Memory Module Virtualization Implementation
*
* Copyright(C) 2015 Intel Corporation.
*
* Author:
* Xiao Guangrong <guangrong.xiao@linux.intel.com>
*
* Currently, it only supports PMEM Virtualization.
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, see <http://www.gnu.org/licenses/>
*/
#include "qemu/osdep.h"
#include "qemu/module.h"
#include "qemu/pmem.h"
#include "qapi/error.h"
#include "qapi/visitor.h"
#include "hw/mem/nvdimm.h"
#include "hw/qdev-properties.h"
#include "hw/mem/memory-device.h"
#include "sysemu/hostmem.h"
static void nvdimm_get_label_size(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
NVDIMMDevice *nvdimm = NVDIMM(obj);
uint64_t value = nvdimm->label_size;
visit_type_size(v, name, &value, errp);
}
static void nvdimm_set_label_size(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
NVDIMMDevice *nvdimm = NVDIMM(obj);
uint64_t value;
if (nvdimm->nvdimm_mr) {
error_setg(errp, "cannot change property value");
return;
}
error: Eliminate error_propagate() with Coccinelle, part 1 When all we do with an Error we receive into a local variable is propagating to somewhere else, we can just as well receive it there right away. Convert if (!foo(..., &err)) { ... error_propagate(errp, err); ... return ... } to if (!foo(..., errp)) { ... ... return ... } where nothing else needs @err. Coccinelle script: @rule1 forall@ identifier fun, err, errp, lbl; expression list args, args2; binary operator op; constant c1, c2; symbol false; @@ if ( ( - fun(args, &err, args2) + fun(args, errp, args2) | - !fun(args, &err, args2) + !fun(args, errp, args2) | - fun(args, &err, args2) op c1 + fun(args, errp, args2) op c1 ) ) { ... when != err when != lbl: when strict - error_propagate(errp, err); ... when != err ( return; | return c2; | return false; ) } @rule2 forall@ identifier fun, err, errp, lbl; expression list args, args2; expression var; binary operator op; constant c1, c2; symbol false; @@ - var = fun(args, &err, args2); + var = fun(args, errp, args2); ... when != err if ( ( var | !var | var op c1 ) ) { ... when != err when != lbl: when strict - error_propagate(errp, err); ... when != err ( return; | return c2; | return false; | return var; ) } @depends on rule1 || rule2@ identifier err; @@ - Error *err = NULL; ... when != err Not exactly elegant, I'm afraid. The "when != lbl:" is necessary to avoid transforming if (fun(args, &err)) { goto out } ... out: error_propagate(errp, err); even though other paths to label out still need the error_propagate(). For an actual example, see sclp_realize(). Without the "when strict", Coccinelle transforms vfio_msix_setup(), incorrectly. I don't know what exactly "when strict" does, only that it helps here. The match of return is narrower than what I want, but I can't figure out how to express "return where the operand doesn't use @err". For an example where it's too narrow, see vfio_intx_enable(). Silently fails to convert hw/arm/armsse.c, because Coccinelle gets confused by ARMSSE being used both as typedef and function-like macro there. Converted manually. Line breaks tidied up manually. One nested declaration of @local_err deleted manually. Preexisting unwanted blank line dropped in hw/riscv/sifive_e.c. Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20200707160613.848843-35-armbru@redhat.com>
2020-07-07 19:06:02 +03:00
if (!visit_type_size(v, name, &value, errp)) {
return;
}
if (value < MIN_NAMESPACE_LABEL_SIZE) {
error_setg(errp, "Property '%s.%s' (0x%" PRIx64 ") is required"
" at least 0x%lx", object_get_typename(obj), name, value,
MIN_NAMESPACE_LABEL_SIZE);
return;
}
nvdimm->label_size = value;
}
static void nvdimm_get_uuid(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
NVDIMMDevice *nvdimm = NVDIMM(obj);
char *value = NULL;
value = qemu_uuid_unparse_strdup(&nvdimm->uuid);
visit_type_str(v, name, &value, errp);
g_free(value);
}
static void nvdimm_set_uuid(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
NVDIMMDevice *nvdimm = NVDIMM(obj);
char *value;
if (!visit_type_str(v, name, &value, errp)) {
return;
}
if (qemu_uuid_parse(value, &nvdimm->uuid) != 0) {
error_setg(errp, "Property '%s.%s' has invalid value",
object_get_typename(obj), name);
}
g_free(value);
}
static void nvdimm_init(Object *obj)
{
object_property_add(obj, NVDIMM_LABEL_SIZE_PROP, "int",
nvdimm_get_label_size, nvdimm_set_label_size, NULL,
qom: Drop parameter @errp of object_property_add() & friends The only way object_property_add() can fail is when a property with the same name already exists. Since our property names are all hardcoded, failure is a programming error, and the appropriate way to handle it is passing &error_abort. Same for its variants, except for object_property_add_child(), which additionally fails when the child already has a parent. Parentage is also under program control, so this is a programming error, too. We have a bit over 500 callers. Almost half of them pass &error_abort, slightly fewer ignore errors, one test case handles errors, and the remaining few callers pass them to their own callers. The previous few commits demonstrated once again that ignoring programming errors is a bad idea. Of the few ones that pass on errors, several violate the Error API. The Error ** argument must be NULL, &error_abort, &error_fatal, or a pointer to a variable containing NULL. Passing an argument of the latter kind twice without clearing it in between is wrong: if the first call sets an error, it no longer points to NULL for the second call. ich9_pm_add_properties(), sparc32_ledma_realize(), sparc32_dma_realize(), xilinx_axidma_realize(), xilinx_enet_realize() are wrong that way. When the one appropriate choice of argument is &error_abort, letting users pick the argument is a bad idea. Drop parameter @errp and assert the preconditions instead. There's one exception to "duplicate property name is a programming error": the way object_property_add() implements the magic (and undocumented) "automatic arrayification". Don't drop @errp there. Instead, rename object_property_add() to object_property_try_add(), and add the obvious wrapper object_property_add(). Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20200505152926.18877-15-armbru@redhat.com> [Two semantic rebase conflicts resolved]
2020-05-05 18:29:22 +03:00
NULL);
object_property_add(obj, NVDIMM_UUID_PROP, "QemuUUID", nvdimm_get_uuid,
qom: Drop parameter @errp of object_property_add() & friends The only way object_property_add() can fail is when a property with the same name already exists. Since our property names are all hardcoded, failure is a programming error, and the appropriate way to handle it is passing &error_abort. Same for its variants, except for object_property_add_child(), which additionally fails when the child already has a parent. Parentage is also under program control, so this is a programming error, too. We have a bit over 500 callers. Almost half of them pass &error_abort, slightly fewer ignore errors, one test case handles errors, and the remaining few callers pass them to their own callers. The previous few commits demonstrated once again that ignoring programming errors is a bad idea. Of the few ones that pass on errors, several violate the Error API. The Error ** argument must be NULL, &error_abort, &error_fatal, or a pointer to a variable containing NULL. Passing an argument of the latter kind twice without clearing it in between is wrong: if the first call sets an error, it no longer points to NULL for the second call. ich9_pm_add_properties(), sparc32_ledma_realize(), sparc32_dma_realize(), xilinx_axidma_realize(), xilinx_enet_realize() are wrong that way. When the one appropriate choice of argument is &error_abort, letting users pick the argument is a bad idea. Drop parameter @errp and assert the preconditions instead. There's one exception to "duplicate property name is a programming error": the way object_property_add() implements the magic (and undocumented) "automatic arrayification". Don't drop @errp there. Instead, rename object_property_add() to object_property_try_add(), and add the obvious wrapper object_property_add(). Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20200505152926.18877-15-armbru@redhat.com> [Two semantic rebase conflicts resolved]
2020-05-05 18:29:22 +03:00
nvdimm_set_uuid, NULL, NULL);
}
static void nvdimm_finalize(Object *obj)
{
NVDIMMDevice *nvdimm = NVDIMM(obj);
g_free(nvdimm->nvdimm_mr);
}
static void nvdimm_prepare_memory_region(NVDIMMDevice *nvdimm, Error **errp)
{
PCDIMMDevice *dimm = PC_DIMM(nvdimm);
uint64_t align, pmem_size, size;
MemoryRegion *mr;
g_assert(!nvdimm->nvdimm_mr);
if (!dimm->hostmem) {
error_setg(errp, "'" PC_DIMM_MEMDEV_PROP "' property must be set");
return;
}
mr = host_memory_backend_get_memory(dimm->hostmem);
align = memory_region_get_alignment(mr);
size = memory_region_size(mr);
pmem_size = size - nvdimm->label_size;
nvdimm->label_data = memory_region_get_ram_ptr(mr) + pmem_size;
pmem_size = QEMU_ALIGN_DOWN(pmem_size, align);
if (size <= nvdimm->label_size || !pmem_size) {
HostMemoryBackend *hostmem = dimm->hostmem;
error_setg(errp, "the size of memdev %s (0x%" PRIx64 ") is too "
"small to contain nvdimm label (0x%" PRIx64 ") and "
"aligned PMEM (0x%" PRIx64 ")",
object_get_canonical_path_component(OBJECT(hostmem)),
memory_region_size(mr), nvdimm->label_size, align);
return;
}
if (!nvdimm->unarmed && memory_region_is_rom(mr)) {
HostMemoryBackend *hostmem = dimm->hostmem;
error_setg(errp, "'unarmed' property must be off since memdev %s "
"is read-only",
object_get_canonical_path_component(OBJECT(hostmem)));
return;
}
nvdimm->nvdimm_mr = g_new(MemoryRegion, 1);
memory_region_init_alias(nvdimm->nvdimm_mr, OBJECT(dimm),
"nvdimm-memory", mr, 0, pmem_size);
memory_region_set_nonvolatile(nvdimm->nvdimm_mr, true);
nvdimm->nvdimm_mr->align = align;
}
static MemoryRegion *nvdimm_md_get_memory_region(MemoryDeviceState *md,
Error **errp)
{
NVDIMMDevice *nvdimm = NVDIMM(md);
Error *local_err = NULL;
if (!nvdimm->nvdimm_mr) {
nvdimm_prepare_memory_region(nvdimm, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return NULL;
}
}
return nvdimm->nvdimm_mr;
}
static void nvdimm_realize(PCDIMMDevice *dimm, Error **errp)
{
NVDIMMDevice *nvdimm = NVDIMM(dimm);
if (!nvdimm->nvdimm_mr) {
nvdimm_prepare_memory_region(nvdimm, errp);
}
}
/*
* the caller should check the input parameters before calling
* label read/write functions.
*/
static void nvdimm_validate_rw_label_data(NVDIMMDevice *nvdimm, uint64_t size,
uint64_t offset)
{
assert((nvdimm->label_size >= size + offset) && (offset + size > offset));
}
static void nvdimm_read_label_data(NVDIMMDevice *nvdimm, void *buf,
uint64_t size, uint64_t offset)
{
nvdimm_validate_rw_label_data(nvdimm, size, offset);
memcpy(buf, nvdimm->label_data + offset, size);
}
static void nvdimm_write_label_data(NVDIMMDevice *nvdimm, const void *buf,
uint64_t size, uint64_t offset)
{
MemoryRegion *mr;
PCDIMMDevice *dimm = PC_DIMM(nvdimm);
bool is_pmem = object_property_get_bool(OBJECT(dimm->hostmem),
"pmem", NULL);
uint64_t backend_offset;
nvdimm_validate_rw_label_data(nvdimm, size, offset);
if (!is_pmem) {
memcpy(nvdimm->label_data + offset, buf, size);
} else {
pmem_memcpy_persist(nvdimm->label_data + offset, buf, size);
}
mr = host_memory_backend_get_memory(dimm->hostmem);
backend_offset = memory_region_size(mr) - nvdimm->label_size + offset;
memory_region_set_dirty(mr, backend_offset, size);
}
static Property nvdimm_properties[] = {
DEFINE_PROP_BOOL(NVDIMM_UNARMED_PROP, NVDIMMDevice, unarmed, false),
DEFINE_PROP_END_OF_LIST(),
};
static void nvdimm_class_init(ObjectClass *oc, void *data)
{
PCDIMMDeviceClass *ddc = PC_DIMM_CLASS(oc);
MemoryDeviceClass *mdc = MEMORY_DEVICE_CLASS(oc);
NVDIMMClass *nvc = NVDIMM_CLASS(oc);
DeviceClass *dc = DEVICE_CLASS(oc);
ddc->realize = nvdimm_realize;
mdc->get_memory_region = nvdimm_md_get_memory_region;
device_class_set_props(dc, nvdimm_properties);
nvc->read_label_data = nvdimm_read_label_data;
nvc->write_label_data = nvdimm_write_label_data;
set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
}
static TypeInfo nvdimm_info = {
.name = TYPE_NVDIMM,
.parent = TYPE_PC_DIMM,
.class_size = sizeof(NVDIMMClass),
.class_init = nvdimm_class_init,
.instance_size = sizeof(NVDIMMDevice),
.instance_init = nvdimm_init,
.instance_finalize = nvdimm_finalize,
};
static void nvdimm_register_types(void)
{
type_register_static(&nvdimm_info);
}
type_init(nvdimm_register_types)