There were several different ways to deal with the situation where the
vector specified for a msix function is out of bound:
- early return a function and keep progresssing
- propagate the error to the caller
- mark msix unusable
- assert it is in bound
- just ignore
An out-of-bound vector should not be specified if the device
implementation is correct so let msix functions always assert that the
specified vector is in range.
An exceptional case is virtio-pci, which allows the guest to configure
vectors. For virtio-pci, it is more appropriate to introduce its own
checks because it is sometimes too late to check the vector range in
msix functions.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Message-Id: <20220829083524.143640-1-akihiko.odaki@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Yuval Shaia <yuval.shaia.ml@gmail.com>
Signed-off-by: Akihiko Odaki <<a href="mailto:akihiko.odaki@daynix.com" target="_blank">akihiko.odaki@daynix.com</a>><br>
As per the NVMe Command Set specification Section 3.2.2, if
i) The namespace is formatted to use 16b Guard Protection
Information (i.e., pif = 0) and
ii) The Descriptor Format is not cleared to 0h
Then the copy command should be aborted with the status code of Invalid
Namespace or Format
Fixes: 44219b6029 ("hw/nvme: 64-bit pi support")
Signed-off-by: Francis Pravin Antony Michael Raj <francis.michael@solidigm.com>
Signed-off-by: Jonathan Derrick <jonathan.derrick@solidigm.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Commit 2e53b0b450 ("hw/nvme: Use ioeventfd to handle doorbell
updates") had the unintended effect of disabling batching of CQEs.
This patch changes the sq/cq timers to bottom halfs and instead of
calling nvme_post_cqes() immediately (causing an interrupt per cqe), we
defer the call.
| iops
-----------------+------
baseline | 138k
+cqe batching | 233k
Fixes: 2e53b0b450 ("hw/nvme: Use ioeventfd to handle doorbell updates")
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Jinhao Fan <fanjinhao21s@ict.ac.cn>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Do not enable ioeventfd by default. Let the feature mature a bit before
we consider enabling it by default.
Fixes: 2e53b0b450 ("hw/nvme: Use ioeventfd to handle doorbell updates")
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Jinhao Fan <fanjinhao21s@ict.ac.cn>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Make sure the notifier handler is unregistered in the main loop prior to
cleaning it up.
Fixes: 2e53b0b450 ("hw/nvme: Use ioeventfd to handle doorbell updates")
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Jinhao Fan <fanjinhao21s@ict.ac.cn>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
While it is safe to process the queues when they are empty, skip it if
the event notifier callback was invoked spuriously.
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Jinhao Fan <fanjinhao21s@ict.ac.cn>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Add property "ioeventfd" which is enabled by default. When this is
enabled, updates on the doorbell registers will cause KVM to signal
an event to the QEMU main loop to handle the doorbell updates.
Therefore, instead of letting the vcpu thread run both guest VM and
IO emulation, we now use the main loop thread to do IO emulation and
thus the vcpu thread has more cycles for the guest VM.
Since ioeventfd does not tell us the exact value that is written, it is
only useful when shadow doorbell buffer is enabled, where we check
for the value in the shadow doorbell buffer when we get the doorbell
update event.
IOPS comparison on Linux 5.19-rc2: (Unit: KIOPS)
qd 1 4 16 64
qemu 35 121 176 153
ioeventfd 41 133 258 313
Changes since v3:
- Do not deregister ioeventfd when it was not enabled on a SQ/CQ
Signed-off-by: Jinhao Fan <fanjinhao21s@ict.ac.cn>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Since commit 916b0f0b52 ("hw/nvme: change nvme-ns 'shared' default")
the default value of nvme-ns param 'shared' is set to true, regardless
if there is a nvme-subsys node or not.
On a system without a nvme-subsys node, a namespace will never be able
to be attached to more than one controller, so for this configuration,
it is counterintuitive for this parameter to be set by default.
Force the nvme-ns param 'shared' to false for configurations where
there is no nvme-subsys node, as the namespace will never be able to
attach to more than one controller anyway.
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
When shadow doorbell buffer is enabled, doorbell registers are lazily
updated. The actual queue head and tail pointers are stored in Shadow
Doorbell buffers.
Add trace events for updates on the Shadow Doorbell buffers and EventIdx
buffers. Also add trace event for the Doorbell Buffer Config command.
Signed-off-by: Jinhao Fan <fanjinhao21s@ict.ac.cn>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
[k.jensen: rebased]
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Implement Doorbel Buffer Config command (Section 5.7 in NVMe Spec 1.3)
and Shadow Doorbel buffer & EventIdx buffer handling logic (Section 7.13
in NVMe Spec 1.3). For queues created before the Doorbell Buffer Config
command, the nvme_dbbuf_config function tries to associate each existing
SQ and CQ with its Shadow Doorbel buffer and EventIdx buffer address.
Queues created after the Doorbell Buffer Config command will have the
doorbell buffers associated with them when they are initialized.
In nvme_process_sq and nvme_post_cqe, proactively check for Shadow
Doorbell buffer changes instead of wait for doorbell register changes.
This reduces the number of MMIOs.
In nvme_process_db(), update the shadow doorbell buffer value with
the doorbell register value if it is the admin queue. This is a hack
since hosts like Linux NVMe driver and SPDK do not use shadow
doorbell buffer for the admin queue. Copying the doorbell register
value to the shadow doorbell buffer allows us to support these hosts
as well as spec-compliant hosts that use shadow doorbell buffer for
the admin queue.
Signed-off-by: Jinhao Fan <fanjinhao21s@ict.ac.cn>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
[k.jensen: rebased]
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
'namespace' is misspelled in a bunch of places.
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Message-Id: <20220614104045.85728-3-dgilbert@redhat.com>
Signed-off-by: Laurent Vivier <laurent@vivier.eu>
The internally maintained AEN mask is not cleared on reset. Fix this.
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
This reverts commit d97eee64fe.
The emulated controller correctly accounts for not including bit buckets
in the controller-to-host data transfer, however it doesn't correctly
account for the holes for the on-disk data offsets.
Reported-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
The SRIOV series exposed an issued with how CC register writes are
handled and how CSTS is set in response to that. Specifically, after
applying the SRIOV series, the controller could end up in a state with
CC.EN set to '1' but with CSTS.RDY cleared to '0', causing drivers to
expect CSTS.RDY to transition to '1' but timing out.
Clean this up.
Reviewed-by: Łukasz Gieryk <lukasz.gieryk@linux.intel.com>
Reviewed-by: Lukasz Maniak <lukasz.maniak@linux.intel.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
This patch updates the initialization place for the AER queue, so it’s
initialized once, at controller initialization, and not every time
controller is enabled.
While the original version works for a non-SR-IOV device, as it’s hard
to interact with the controller if it’s not enabled, the multiple
reinitialization is not necessarily correct.
With the SR/IOV feature enabled a segfault can happen: a VF can have its
controller disabled, while a namespace can still be attached to the
controller through the parent PF. An event generated in such case ends
up on an uninitialized queue.
While it’s an interesting question whether a VF should support AER in
the first place, I don’t think it must be answered today.
Signed-off-by: Łukasz Gieryk <lukasz.gieryk@linux.intel.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
With the new command one can:
- assign flexible resources (queues, interrupts) to primary and
secondary controllers,
- toggle the online/offline state of given controller.
Signed-off-by: Łukasz Gieryk <lukasz.gieryk@linux.intel.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
With four new properties:
- sriov_v{i,q}_flexible,
- sriov_max_v{i,q}_per_vf,
one can configure the number of available flexible resources, as well as
the limits. The primary and secondary controller capability structures
are initialized accordingly.
Since the number of available queues (interrupts) now varies between
VF/PF, BAR size calculation is also adjusted.
Signed-off-by: Łukasz Gieryk <lukasz.gieryk@linux.intel.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
An NVMe device with SR-IOV capability calculates the BAR size
differently for PF and VF, so it makes sense to extract the common code
to a separate function.
Signed-off-by: Łukasz Gieryk <lukasz.gieryk@linux.intel.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
The n->reg_size parameter unnecessarily splits the BAR0 size calculation
in two phases; removed to simplify the code.
With all the calculations done in one place, it seems the pow2ceil,
applied originally to reg_size, is unnecessary. The rounding should
happen as the last step, when BAR size includes Nvme registers, queue
registers, and MSIX-related space.
Finally, the size of the mmio memory region is extended to cover the 1st
4KiB padding (see the map below). Access to this range is handled as
interaction with a non-existing queue and generates an error trace, so
actually nothing changes, while the reg_size variable is no longer needed.
--------------------
| BAR0 |
--------------------
[Nvme Registers ]
[Queues ]
[power-of-2 padding] - removed in this patch
[4KiB padding (1) ]
[MSIX TABLE ]
[4KiB padding (2) ]
[MSIX PBA ]
[power-of-2 padding]
Signed-off-by: Łukasz Gieryk <lukasz.gieryk@linux.intel.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
The NVMe device defines two properties: max_ioqpairs, msix_qsize. Having
them as constants is problematic for SR-IOV support.
SR-IOV introduces virtual resources (queues, interrupts) that can be
assigned to PF and its dependent VFs. Each device, following a reset,
should work with the configured number of queues. A single constant is
no longer sufficient to hold the whole state.
This patch tries to solve the problem by introducing additional
variables in NvmeCtrl’s state. The variables for, e.g., managing queues
are therefore organized as:
- n->params.max_ioqpairs – no changes, constant set by the user
- n->(mutable_state) – (not a part of this patch) user-configurable,
specifies number of queues available _after_
reset
- n->conf_ioqpairs - (new) used in all the places instead of the ‘old’
n->params.max_ioqpairs; initialized in realize()
and updated during reset() to reflect user’s
changes to the mutable state
Since the number of available i/o queues and interrupts can change in
runtime, buffers for sq/cqs and the MSIX-related structures are
allocated big enough to handle the limits, to completely avoid the
complicated reallocation. A helper function (nvme_update_msixcap_ts)
updates the corresponding capability register, to signal configuration
changes.
Signed-off-by: Łukasz Gieryk <lukasz.gieryk@linux.intel.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
This patch implements the Function Level Reset, a feature currently not
implemented for the Nvme device, while listed as a mandatory ("shall")
in the 1.4 spec.
The implementation reuses FLR-related building blocks defined for the
pci-bridge module, and follows the same logic:
- FLR capability is advertised in the PCIE config,
- custom pci_write_config callback detects a write to the trigger
register and performs the PCI reset,
- which, eventually, calls the custom dc->reset handler.
Depending on reset type, parts of the state should (or should not) be
cleared. To distinguish the type of reset, an additional parameter is
passed to the reset function.
This patch also enables advertisement of the Power Management PCI
capability. The main reason behind it is to announce the no_soft_reset=1
bit, to signal SR-IOV support where each VF can be reset individually.
The implementation purposedly ignores writes to the PMCS.PS register,
as even such naïve behavior is enough to correctly handle the D3->D0
transition.
It’s worth to note, that the power state transition back to to D3, with
all the corresponding side effects, wasn't and stil isn't handled
properly.
Signed-off-by: Łukasz Gieryk <lukasz.gieryk@linux.intel.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Introduce handling for Secondary Controller List (Identify command with
CNS value of 15h).
Secondary controller ids are unique in the subsystem, hence they are
reserved by it upon initialization of the primary controller to the
number of sriov_max_vfs.
ID reservation requires the addition of an intermediate controller slot
state, so the reserved controller has the address 0xFFFF.
A secondary controller is in the reserved state when it has no virtual
function assigned, but its primary controller is realized.
Secondary controller reservations are released to NULL when its primary
controller is unregistered.
Signed-off-by: Lukasz Maniak <lukasz.maniak@linux.intel.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Implementation of Primary Controller Capabilities data
structure (Identify command with CNS value of 14h).
Currently, the command returns only ID of a primary controller.
Handling of remaining fields are added in subsequent patches
implementing virtualization enhancements.
Signed-off-by: Lukasz Maniak <lukasz.maniak@linux.intel.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
This patch implements initial support for Single Root I/O Virtualization
on an NVMe device.
Essentially, it allows to define the maximum number of virtual functions
supported by the NVMe controller via sriov_max_vfs parameter.
Passing a non-zero value to sriov_max_vfs triggers reporting of SR-IOV
capability by a physical controller and ARI capability by both the
physical and virtual function devices.
NVMe controllers created via virtual functions mirror functionally
the physical controller, which may not entirely be the case, thus
consideration would be needed on the way to limit the capabilities of
the VF.
NVMe subsystem is required for the use of SR-IOV.
Signed-off-by: Lukasz Maniak <lukasz.maniak@linux.intel.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
NVMe command set specification for end-to-end data protection formatted
namespace states:
o If the Reference Tag Check bit of the PRCHK field is set to ‘1’ and
the namespace is formatted for Type 3 protection, then the
controller:
▪ should not compare the protection Information Reference Tag
field to the computed reference tag; and
▪ may ignore the ILBRT and EILBRT fields. If a command is
aborted as a result of the Reference Tag Check bit of the
PRCHK field being set to ‘1’, then that command should be
aborted with a status code of Invalid Protection Information,
but may be aborted with a status code of Invalid Field in
Command.
Currently qemu compares reftag in the nvme_dif_prchk function whenever
Reference Tag Check bit is set in the command. For type 3 namespaces
however, caller of nvme_dif_prchk - nvme_dif_check does not increment
reftag for each subsequent logical block. That way commands incorporating
more than one logical block for type 3 formatted namespaces with reftag
check bit set, always fail with End-to-end Reference Tag Check Error.
Comply with spec by handling case of set Reference Tag Check
bit in the type 3 formatted namespace.
Fixes: 146f720c55 ("hw/block/nvme: end-to-end data protection")
Signed-off-by: Dmitry Tikhov <d.tihov@yadro.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
The Linux kernel quirks the QEMU NVMe controller pretty heavily because
of the namespace identifier mess. Since this is now fixed, bump the
firmware revision number to allow the quirk to be disabled for this
revision.
As of now, bump the firmware revision number to be equal to the QEMU
release version number.
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Do not report the "null uuid" (all zeros) in the namespace
identification descriptors.
Reported-by: Luis Chamberlain <mcgrof@kernel.org>
Reported-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Do not default to generate an UUID for namespaces if it is not
explicitly specified.
This is a technically a breaking change in behavior. However, since the
UUID changes on every VM launch, it is not spec compliant and is of
little use since the UUID cannot be used reliably anyway and the
behavior prior to this patch must be considered buggy.
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
We cannot provide auto-generated unique or persistent namespace
identifiers (EUI64, NGUID, UUID) easily. Since 6.1, namespaces have been
assigned a generated EUI64 of the form "52:54:00:<namespace counter>".
This is will be unique within a QEMU instance, but not globally.
Revert that this is assigned automatically and immediately deprecate the
compatibility parameter. Users can opt-in to this with the
`eui64-default=on` device parameter or set it explicitly with
`eui64=UINT64`.
Cc: libvir-list@redhat.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
The Identify Controller Serial Number (SN) is the serial number for the
NVM subsystem and must be the same across all controller in the NVM
subsystem.
Enforce this.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Pass the right constant to nvme_smart_event(). The NVME_AER* values hold
the bit position in the SMART byte, not the shifted value that we expect
it to be in nvme_smart_event().
Fixes: c62720f137 ("hw/block/nvme: trigger async event during injecting smart warning")
Acked-by: zhenwei pi <pizhenwei@bytedance.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Current implementation have problem in the read part of copy command.
Because there is no metadata mangling before nvme_dif_check invocation,
reftag error could be thrown for blocks of namespace that have not been
previously written to.
Signed-off-by: Dmitry Tikhov <d.tihov@yadro.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Since there is no return after nvme_dsm_cb invocation, metadata
associated with non-zero block range is currently zeroed. Also this
behaviour leads to segfault since we schedule iocb->bh two times.
First when entering nvme_dsm_cb with iocb->idx == iocb->nr and
second because of missing return on call stack unwinding by calling
blk_aio_pwrite_zeroes and subsequent nvme_dsm_cb callback.
Fixes: d7d1474fd8 ("hw/nvme: reimplement dsm to allow cancellation")
Signed-off-by: Dmitry Tikhov <d.tihov@yadro.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Since nlbas is of type int, it does not work with large namespace size
values, e.g., 9 TB size of file backing namespace and 8 byte metadata
with 4096 bytes lbasz gives negative nlbas value, which is later
promoted to negative int64_t type value and results in negative
ns->moff which breaks namespace
Signed-off-by: Dmitry Tikhov <ddtikhov@gmail.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Header guard symbols should match their file name to make guard
collisions less likely.
Cleaned up with scripts/clean-header-guards.pl, followed by some
renaming of new guard symbols picked by the script to better ones.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20220506134911.2856099-2-armbru@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
[Change to generated file ebpf/rss.bpf.skeleton.h backed out]
g_new(T, n) is neater than g_malloc(sizeof(T) * n). It's also safer,
for two reasons. One, it catches multiplication overflowing size_t.
Two, it returns T * rather than void *, which lets the compiler catch
more type errors.
This commit only touches allocations with size arguments of the form
sizeof(T).
Patch created mechanically with:
$ spatch --in-place --sp-file scripts/coccinelle/use-g_new-etc.cocci \
--macro-file scripts/cocci-macro-file.h FILES...
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20220315144156.1595462-4-armbru@redhat.com>
Reviewed-by: Pavel Dovgalyuk <Pavel.Dovgalyuk@ispras.ru>
This adds support for one possible new protection information format
introduced in TP4068 (and integrated in NVMe 2.0): the 64-bit CRC guard
and 48-bit reference tag. This version does not support storage tags.
Like the CRC16 support already present, this uses a software
implementation of CRC64 (so it is naturally pretty slow). But its good
enough for verification purposes.
This may go nicely hand-in-hand with the support that Keith submitted
for the Linux kernel[1].
[1]: https://lore.kernel.org/linux-nvme/20220126165214.GA1782352@dhcp-10-100-145-180.wdc.com/T/
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Naveen Nagar <naveen.n1@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
A subsequent patch will introduce a new tuple size; so add a helper and
use that instead of sizeof() and magic numbers.
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Add support for up to 64 LBA formats through the LBAFEE field of the
Host Behavior Support feature.
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Naveen Nagar <naveen.n1@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
There is no need to extract the format command parameters for each
namespace. Move it to the entry point.
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Add support for getting and setting the Host Behavior Support feature.
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Naveen Nagar <naveen.n1@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Add support for TP 4076 ("Zoned Random Write Area"), v2021.08.23
("Ratified").
This adds three new namespace parameters: "zoned.numzrwa" (number of
zrwa resources, i.e. number of zones that can have a zrwa),
"zoned.zrwas" (zrwa size in LBAs), "zoned.zrwafg" (granularity in LBAs
for flushes).
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Add struct for Zone Management Send in preparation for more zone send
flags.
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
These buffers can be anything, not an array of chars,
so use the 'void *' type for them.
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
The 'buf' argument is not modified, so better pass it as const type.
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
This fixes CVE-2021-3929 "locally" by denying DMA to the iomem of the
device itself. This still allows DMA to MMIO regions of other devices
(e.g. doing P2P DMA to the controller memory buffer of another NVMe
device).
Fixes: CVE-2021-3929
Reported-by: Qiuhao Li <Qiuhao.Li@outlook.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Since commit 292e13142d, dma_buf_rw() returns a MemTxResult type.
Do not discard it, return it to the caller. Pass the previously
returned value (the QEMUSGList residual size, which was rarely used)
as an optional argument.
With this new API, SCSIRequest::residual might now be accessed via
a pointer. Since the size_t type does not have the same size on
32 and 64-bit host architectures, convert it to a uint64_t, which
is big enough to hold the residual size, and the type is constant
on both 32/64-bit hosts.
Update the few dma_buf_read() / dma_buf_write() callers to the new
API.
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Acked-by: Peter Xu <peterx@redhat.com>
Message-Id: <20220117125130.131828-1-f4bug@amsat.org>
Update the obvious places where dma_addr_t should be used
(instead of uint64_t, hwaddr, size_t, int32_t types).
This allows to have &dma_addr_t type portable on 32/64-bit
hosts.
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-Id: <20220111184309.28637-11-f4bug@amsat.org>
Let devices specify transaction attributes when calling
dma_buf_read().
Keep the default MEMTXATTRS_UNSPECIFIED in the few callers.
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20211223115554.3155328-13-philmd@redhat.com>
Let devices specify transaction attributes when calling
dma_buf_write().
Keep the default MEMTXATTRS_UNSPECIFIED in the few callers.
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20211223115554.3155328-12-philmd@redhat.com>
Change namespaces to be shared namespaces by default (parameter
shared=on). Keep shared=off for older machine types.
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
With commit 5ffbaeed16 ("hw/nvme: fix controller hot unplugging")
namespaces get moved from the controller to the subsystem if one
is specified.
That keeps the namespaces alive after a controller hot-unplug, but
after a controller hotplug we have to reconnect the namespaces
from the subsystem to the controller.
Fixes: 5ffbaeed16 ("hw/nvme: fix controller hot unplugging")
Cc: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Hannes Reinecke <hare@suse.de>
[k.jensen: only attach to shared and non-detached namespaces]
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Rename qbus_create_inplace() to qbus_init(); this is more in line
with our usual naming convention for functions that in-place
initialize objects.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-id: 20210923121153.23754-5-peter.maydell@linaro.org
Currently, FUSED operations are not supported by QEMU. As per the 1.4 SPEC,
controller should abort the command that requested a fused operation with
an INVALID FIELD error code if they are not supported.
Changes from v1:
Added FUSE flag check also to the admin cmd processing as the FUSED
operations are mentioned in the general SQE section in the SPEC.
Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Fix is added to check for reserved value in select field for
namespace attachment
CC: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Naveen Nagar <naveen.n1@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Address 0x0 is a valid address. Fix the admin submission and completion
queue address validation to not error out on this.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Coverity found that 'uuid', 'csi' and 'eui64' are uninitialized. While
we set most of the fields, we do not explicitly set the rsvd2 field in
the NvmeIdNsDescr header.
Fix this by explicitly zero-initializing the variables.
Reported-by: Coverity (CID 1458835, 1459295 and 1459580)
Fixes: 6870cfb814 ("hw/nvme: namespace parameter for EUI-64")
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
The new PMR test unearthed a long-standing issue with MMIO reads on
big-endian hosts.
Fix this by unconditionally storing all controller registers in little
endian.
Cc: Gollu Appalanaidu <anaidu.gollu@samsung.com>
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Peter noticed that mmio access may read into the NvmeParams member in
the NvmeCtrl struct.
Fix the bounds check.
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Add the NvmeBarRegs enum and use these instead of explicit register
offsets.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Gollu Appalanaidu <anaidu.gollu@samsung.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
The specification uses a set of 32 bit PMRMSCL and PMRMSCU registers to
make up the 64 bit logical PMRMSC register.
Make it so.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Prior to this patch the nvme-ns devices are always children of the
NvmeBus owned by the NvmeCtrl. This causes the namespaces to be
unrealized when the parent device is removed. However, when subsystems
are involved, this is not what we want since the namespaces may be
attached to other controllers as well.
This patch adds an additional NvmeBus on the subsystem device. When
nvme-ns devices are realized, if the parent controller device is linked
to a subsystem, the parent bus is set to the subsystem one instead. This
makes sure that namespaces are kept alive and not unrealized.
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
If the number of PRP/SGL mappings exceed 1024, reads and writes will
fail because of an internal QEMU limitation of max 1024 vectors.
Signed-off-by: Padmakar Kalghatgi <p.kalghatgi@samsung.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
[k.jensen: changed the error message to be more generic]
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Make sure the controller is unregistered from the subsystem when device
is removed.
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
We currently lack the infrastructure to handle subsystem hotplugging, so
disable it.
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
The nvme_ns_setup and nvme_ns_check_constraints should not depend on the
controller state. Refactor and remove it.
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Jakub noticed[1] that, when using pin-based interrupts, the device will
unconditionally deasssert when any CQEs are acknowledged. However, the
pin should not be deasserted if other completion queues still holds
unacknowledged CQEs.
The bug is an artifact of commit ca247d3509 ("hw/block/nvme: fix
pin-based interrupt behavior") which fixed one bug but introduced
another. This is the third time someone tries to fix pin-based
interrupts (see commit 5e9aa92eb1 ("hw/block: Fix pin-based interrupt
behaviour of NVMe"))...
Third time's the charm, so fix it, again, by keeping track of how many
CQs have unacknowledged CQEs and only deassert when all are cleared.
[1]: <20210610114624.304681-1-jakub.jermar@kernkonzept.com>
Cc: qemu-stable@nongnu.org
Fixes: ca247d3509 ("hw/block/nvme: fix pin-based interrupt behavior")
Reported-by: Jakub Jermář <jakub.jermar@kernkonzept.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Qiang Liu reported that an access on an unknown address is triggered in
memory_region_set_enabled because a check on CAP.PMRS is missing for the
PMRCTL register write when no PMR is configured.
Cc: qemu-stable@nongnu.org
Fixes: 75c3c9de96 ("hw/block/nvme: disable PMR at boot up")
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/362
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
In the documentation of the '-detached' param "be" and "not" has been
used side by side, fix that.
Signed-off-by: Gollu Appalanaidu <anaidu.gollu@samsung.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Add the controller identifiers list CNS 0x13, available list of ctrls
in NVM Subsystem that may or may not be attached to namespaces.
In Identify Ctrl List of the CNS 0x12 and 0x13 no endian conversion
for the nsid field.
These two CNS values shows affect when there exists a Subsystem.
Added condition if there is no Subsystem return invalid field in
command.
Signed-off-by: Gollu Appalanaidu <anaidu.gollu@samsung.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
This partially reverts commit 98f84f5a4e.
Since all "multi aio" commands are now reimplemented to properly track
the nested aiocbs, we can revert the "hack" that was introduced to make
sure all requests we're properly drained upon sq deletion.
The revert is partial since we keep the assert that no outstanding
requests remain on the submission queue after the explicit cancellation.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Prior to this patch, the aios associated with broadcast format are
submitted anonymously (no aiocb reference saved from the blk_aio call).
Fix this by formatting the namespaces one after another, saving a
reference to the aiocb for each.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Prior to this patch, the aios associated with zone reset are submitted
anonymously (no reference saved to the aiocb from the blk_aio call).
Fix this by resetting the zones one after another, saving a reference to
the aiocb for each reset.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Before this patch the code would issue several aios simultaneously
without saving a reference to the aiocb. Without the aiocb reference the
individual copies cannot be canceled.
Fix this by issuing copies of the ranges one after another.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Some commands report additional useful information in dw0 and dw1 of the
completion queue entry.
Add them to the trace.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
The nvme_check_prinfo() and nvme_dif_check() functions operate on the
16 bit "control" member of the NvmeCmd. These functions do not otherwise
operate on an NvmeCmd or an NvmeRequest, so change them to expect the
actual 4 bit PRINFO field and add constants that work on this field as
well.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Make nvme_get_zone_by_slba() return NULL if the slba is out of range.
This allows the function to be used without guarding the call with a
call to nvme_check_bounds(), in preparation for the next patch.
Add asserts after calling nvme_get_zone_by_slba() instead.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Prepare nvme_dif_pract_generate_dif() and nvme_dif_check() to be
callable in smaller increments by making the reftag a pointer parameter
updated by the function.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Prior to this patch, a loop was used to issue multiple "fire and forget"
aios for each range in the command. Without a reference to the aiocb
returned from the blk_aio_pdiscard calls, the aios cannot be canceled.
Fix this by processing the ranges one after another.
As a bonus, this fixes how metadata is cleared (i.e. we only zero it out
if the data was succesfully discarded).
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Pull the gist of nvme_check_dulbe() into a helper function. This is in
preparation for dsm refactoring.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Prior to this patch, a broadcast flush would result in submitting
multiple "fire and forget" aios (no reference saved to the aiocbs
returned from the blk_aio_flush calls).
Fix this by issuing the flushes one after another.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
On machines with version > 6.0 replace a missing EUI-64 by a generated
value.
Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
The EUI-64 field is the only identifier for NVMe namespaces in UEFI device
paths. Add a new namespace property "eui64", that provides the user the
option to specify the EUI-64.
Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Acked-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
As per the TP 4056d Namespace types CNS 0x00 and CNS 0x11
CSI field shouldn't use but it is being used for these two
Identify command CNS values, fix that.
Remove 'nvme_csi_has_nvm_support()' helper as suggested by
Klaus we can safely assume NVM command set support for all
namespaces.
Suggested-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Gollu Appalanaidu <anaidu.gollu@samsung.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
In the Zoned Namespace Command Set Specification, chapter
2.5.1 Managing resources
"The controller may transition zones in the ZSIO:Implicitly Opened state
to the ZSC:Closed state for resource management purposes."
The word may in this sentence means that automatically transitioning
an implicitly opened zone to closed is completely optional.
Add a new parameter so that the user can control if this automatic
transitioning should be performed or not.
Being able to control this can help with verifying that e.g. a user-space
program behaves properly even without this optional ZNS feature.
The default value is set to true, in order to not change the existing
behavior.
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
[k.jensen: moved parameter to controller]
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Currently LBAF formats are being intialized based on metadata
size if and only if nvme-ns "ms" parameter is non-zero value.
Since FormatNVM command being supported device parameter "ms"
may not be the criteria to initialize the supported LBAFs.
And make LBAF array as read-only.
Signed-off-by: Gollu Appalanaidu <anaidu.gollu@samsung.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Add enums for the Identify Namespace FLBAS and MC fields.
Signed-off-by: Gollu Appalanaidu <anaidu.gollu@samsung.com>
[k.jensen: squashed separate flbas/mc commits into one]
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
With the introduction of the nvme-subsystem device we are really
cluttering up the hw/block directory.
As suggested by Philippe previously, move the nvme emulation to hw/nvme.
Suggested-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
