I'm working on a Linux kernel project and i need to find a way to allocate Virtual Memory without allocating Physical Memory. For example if I use this :
char* buffer = my_virtual_mem_malloc(sizeof(char) * 512);
my_virtual_mem_malloc is a new SYSCALL implemented by my kernel module. All data written on this buffer is stocked on file or on other server by using socket (not on Physical Memory). So to complete this job, i need to request Virtual Memory and get access to the vm_area_struct structure to redefine vm_ops struct.
Do you have any ideas about this ?
thx
This is not architecturally possible. You can create vm areas that have a writeback routine that copies data somewhere, but at some level, you must allocate physical pages to be written to.
If you're okay with that, you can simply write a FUSE driver, mount it somewhere, and mmap a file from it. If you're not, then you'll have to just write(), because redirecting writes without allocating a physical page at all is not supported by the x86, at the very least.
There are a few approaches to this problem, but most of them require you to first write to an intermediate memory.
Network File System (NFS)
The easiest approach is simply to have the server open some sort of a shared file system such as NFS and using mmap() to map a remote file to a memory address. Then, writing to that address will actually write the OS's page cache, wich will eventually be written to the remote file when the page cache is full or after predefined system timeout.
Distributed Shared Memory (DSM)
An alternative approach is using DSM with a very small cache size.
In computer science, distributed shared memory (DSM) is a form of memory architecture where physically separated memories can be addressed as one logically shared address space.
[...] Software DSM systems can be implemented in an operating system, or as a programming library and can be thought of as extensions of the underlying virtual memory architecture. When implemented in the operating system, such systems are transparent to the developer; which means that the underlying distributed memory is completely hidden from the users.
It means that each virtual address is logically mapped to a virtual address on a remote machine and writing to it will do the following: (a) receive the page from the remote machine and gain exclusive access. (b) update the page data. (c) release the page and send it back to the remote machine when it reads it again.
On typical DSM implementation, (c) will only happen when the remote machine will read the data again, but you might start from existing DSM implementation and change the behavior so that the data is sent once the local machine page cache is full.
I/O MMU
[...] the IOMMU maps device-visible virtual addresses (also called device addresses or I/O addresses in this context) to physical addresses.
This basically means to write directly to the network device buffer, which is actually implementing an alternative driver for that device.
Such approach seems the most complicated and I don't see any benefit from that approach.
This approach is actually not using any intermediate memory but is definitely not recommended unless the system has a heavy realtime requirement.
Related
when a program started the OS will create a virtual memory, which divided into stack, heap, data, text to run a process on it.I know that each segment is used for specification purpose such as text saves the binary code of program, data saves static and global variable. My question is why the OS need to create the virtual memory and divide it into the segments ? How about if OS just use the physical memory and the process run directly on the physical memory. I think maybe the answer is related with running many process at the same time, sharing memory between process but i am not sure. It is kind if you give me an example about the benefit of creating virtual memory and dividing it into the segments.
In an environment with memory protection via a memory mapping unit, all memory is virtual (mapped via the MMU). It's possible to simply map each virtual address linearly to physical addresses, while still using the protection capabilities of the MMU, but doing that makes no sense. There are many reasons to prefer that memory not be directly mappped, such as being able to share program instructions and shared library code between instances of the same program or different programs, being able to fork, etc.
I'm developing a new Kernel-Mode driver, that should run on Windows 10 (64-bit).
This driver should allocate 48GB of continuous physical memory, and map it (its base address) to a virtual address in the user space of the Windows application that will use it. The system actually has 64GB of RAM installed on it, so it might be needed to make a segment of the memory dedicated for this use, perhaps by changing a boot entry information.
In addition, the driver should reveal its base address somehow to an FPGA-based device, located on the PCIe slot. The purpose of this, is to use this 48GB of continuous physical allocated memory, as a DMA (Direct Memory Access). Namely, the FPGA-based device will generate data, and write it at the appropriate location in the DMA. The host software will try to read from that location, in a cyclic fashion. That is, the FPGA will override the data in the buffer, and the host will try to keep the pace, and read that data before it is overridden.
Please note that this question only deals with the host side (the driver), and not with the FPGA side.
So, basically my questions are:
How do I make such an allocation (as described above)?
How do I map the base address from the virtual address in the Kernel-Space, to the appropriate virtual address in the User-Space?
How do I reveal that base address to the FPGA (located on the PCIe slot), so it will know where to perform its write operations?
What other Callback-Functions should this driver implement, in terms of events handling?
Thanks a lot!
i'm a newbie experimenting a project using rdma (ib_verbs) in kernel module. I got the example code from krping and tinkering on it. The system run on 64bits Linux Centos with a custom 3.10 Linux kernel that require transparent huge pages disabled.
I want a large (4GB up) of RDMA read/write able space which doesn't have to be contiguous as i'll most likely write/read at most 1MB at a time from remote party (random access).
Question:
Should i just do a thousand times of 4MB kmalloc and register DMA region? How bad it is, design wise for allocating large chuck of memory using kmalloc instead of vmalloc? I heard it should not be done and large memory should only retrieved via vmalloc. But addresses from vmalloc are not good for DMA.
If not then what would be a good alternative way to have a 4GB buffer that can be random access from remote party?
How does user-space rdma manage this kind of buffer? I remembered that i only malloc 4GB of memory and call ibv_reg_mr and it is ready to use.
As long as you're not using a memory that covers the entire physical memory (which isn't recommended for write-enabled MRs), you should use the IB_WR_REG_MR work request to register your memory region. For that, you would use the ib_map_mr_sg function which accepts a scatterlist and a page size. So basically, you can register an MR that is built with chunks of a fixed size that you choose.
There's a tradeoff here: using small allocation size will allow the kernel to find free memory easier on fragmented systems, but on the other hand it could decrease performance, as it can increase the load on the NIC's IOTLB.
User-space handles large MR registration by calling get_user_pages and using the system's page size (normally 4kb). Though some drivers have optimizations to try and detect larger page sizes internally, if the user-space memory happens to align that way.
I'm new in Linux world, and would like to ask a question for this forum:
If I want to access physical address from user space, and I don't have any Kernel driver implementation for this specific hardware device - Can I do it?
I know this is not the "right" way to do so, just want to know if there is a way.
Thanks in advanced!
You cannot in general access physical addresses (from user-space program) on Linux.
However, you might perhaps want to mmap(2) the /dev/mem device (see mem(4) for details).
You'll still use virtual memory with virtual addresses, but you'll happen to see part of the physical RAM.
Read Advanced Linux Programming.
No it is not possible to access an arbitrary physical address from application without a system call. (That means you need an existing driver or you need to write a kernel space driver to do map required register for you)
Mmap also work on virtual address. So if your physical addresses maps to a logical address then only you can get a mapping of the wanted physical address and access it.
Depending on your hardware architecture you might not be able to directly access the address of a register because of the memory protection mechanics and because memory addresses "seen" by the kernel are different from the one seen from a user space process.
You will need some kernel space code that will map back and forth the register address to a memory address that makes sense for your user speca process. Try reading about memory mapping and mmap () related syscalls
I understand that each user process is given a virtual address space, and that can be dumped. But is there a way to dump the Physical Address Space? Suppose I have 32-bit system with 4GB memory, can i write a program to print each physical memory location.
I understand it violates memory protection etc. but if its possible how can convert this into a kernel process or lower level process to allow me access to the entire memory..?
I'd like to know how to write such code (if possible) on Windows/Linux platform( or kernel).. OR in case I've to use Assembly or something like that, how to shift to that privilege level.
In Linux, you can open and map the device file /dev/mem (if you have read permission to it). This corresponds to physical memory.
can i write a program to print each physical memory location.
I think no operating system gives the user access to physical memory location. So, you cann't. What ever, you are seeing are virtual addresses produced by the Operating System.
It is possible, on Windows, to access physical memory directly. Some of the things you can do:
Use the Device\PhysicalMemory object -- you can't access all physical memory, and user-mode access to it is restricted starting from Windows Server 2003 SP1.
Use Address Windowing Extensions -- you can control your own virtual-to-physical address mappings, so in a sense you are accessing physical memory directly, although still through page tables.
Write a kernel-mode driver -- there are kernel-mode APIs to access physical memory directly, to allocate physical memory pages, etc. One reason for that is DMA (Direct Memory Access).
None of these methods will give you easy, unrestricted access to any physical memory location.
If I may ask, what are you trying to accomplish?
I'm thinking you could probably do it with a kernel mode driver, but the result would be gibberish as what is in the user section of RAM at the time you grabbed it would be what the OS had paged in, it may be part of one application or a mish mash of a whole bunch. This previous SO question may also be helpful: How does a Windows Kernel mode Driver, access paged memory ?
Try this NTMIO - A WINDOWS COMMAND LINE TO ACCESS HARDWARE RESOURCES http://siliconkit.com/ocart/index.php?route=product/product&keyword=ntmio&category_id=0&product_id=285