Instead of relying on raising the TPL to protect the critical sections
that manipulate the global bitmask that keeps track of bounce buffer
allocations, use compare-and-exchange to manage the global variable, and
tweak the logic to line up with that.
Given that IoMmuDxe implements a singleton protocol that is shared
between multiple drivers, and considering the elaborate and confusing
requirements in the UEFP spec regarding TPL levels at which protocol
methods may be invoked, not relying on TPL levels at all is a more
robust approach in this case.
Link: https://bugzilla.redhat.com/show_bug.cgi?id=2211060
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Pedro Falcato <pedro.falcato@gmail.com>
Searching for an unused bounce buffer in mReservedMemBitmap and
reserving the buffer by flipping the bit is a critical section
which must not be interrupted. Raise the TPL level to ensure
that.
Without this fix it can happen that IoMmuDxe hands out the same
bounce buffer twice, causing trouble down the road. Seen happening
in practice with VirtioNetDxe setting up the network interface (and
calling into IoMmuDxe from a polling timer callback) in parallel with
Boot Manager doing some disk I/O. An ASSERT() in VirtioNet caught
the buffer inconsistency.
Full story with lots of details and discussions is available here:
https://bugzilla.redhat.com/show_bug.cgi?id=2211060
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
__FUNCTION__ is a pre-standard extension that gcc and Visual C++ among
others support, while __func__ was standardized in C99.
Since it's more standard, replace __FUNCTION__ with __func__ throughout
OvmfPkg.
Signed-off-by: Rebecca Cran <rebecca@bsdio.com>
Reviewed-by: Michael D Kinney <michael.d.kinney@intel.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Sunil V L <sunilvl@ventanamicro.com>
Add support to use the reserved shared memory within the IoMmu library.
This improves boot times for all SEV guests, with SEV-SNP benefiting the
most as it avoids the page state change call to the hypervisor.
Cc: Erdem Aktas <erdemaktas@google.com>
Cc: James Bottomley <jejb@linux.ibm.com>
Cc: Jiewen Yao <jiewen.yao@intel.com>
Cc: Min Xu <min.m.xu@intel.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Acked-by: Jiewen Yao <Jiewen.yao@intel.com>
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
BZ: https://bugzilla.tianocore.org/show_bug.cgi?id=4171
A typical QEMU fw_cfg read bytes with IOMMU for td guest is that:
(QemuFwCfgReadBytes@QemuFwCfgLib.c is the example)
1) Allocate DMA Access buffer
2) Map actual data buffer
3) start the transfer and wait for the transfer to complete
4) Free DMA Access buffer
5) Un-map actual data buffer
In step 1/2, Private memories are allocated, converted to shared memories.
In Step 4/5 the shared memories are converted to private memories and
accepted again. The final step is to free the pages.
This is time-consuming and impacts td guest's boot perf (both direct boot
and grub boot) badly.
In a typical grub boot, there are about 5000 calls of page allocation and
private/share conversion. Most of page size is less than 32KB.
This patch allocates a memory region and initializes it into pieces of
memory with different sizes. A piece of such memory consists of 2 parts:
the first page is of private memory, and the other pages are shared
memory. This is to meet the layout of common buffer.
When allocating bounce buffer in IoMmuMap(), IoMmuAllocateBounceBuffer()
is called to allocate the buffer. Accordingly when freeing bounce buffer
in IoMmuUnmapWorker(), IoMmuFreeBounceBuffer() is called to free the
bounce buffer. CommonBuffer is allocated by IoMmuAllocateCommonBuffer
and accordingly freed by IoMmuFreeCommonBuffer.
This feature is tested in Intel TDX pre-production platform. It saves up
to hundreds of ms in a grub boot.
Cc: Erdem Aktas <erdemaktas@google.com>
Cc: James Bottomley <jejb@linux.ibm.com>
Cc: Jiewen Yao <jiewen.yao@intel.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Jiewen Yao <Jiewen.yao@intel.com>
Signed-off-by: Min Xu <min.m.xu@intel.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Ard Biesheuvel
Gerd Hoffmann
Rebecca Cran
Tom Lendacky
Min M Xu