Search code examples
operating-systempaging

How does process start execution under pure demand paging?


I was studying memory management in OS and suddenly got this doubt. It is said that in pure demand paging, process starts execution with zero pages brought to the main memory. The virtual address space contains many things including data, stack,heap and the text-area or code. So if a process is going to execute and it has no page in main memory,how will Instruction register store its first instruction which will executed by CPU resulting in further page faults?


Solution

  • This is a bad way of viewing the address space.

    The virtual address space contains many things including data, stack,heap and the text-area or code.

    The address space consists of memory with different attributes: readonly, readonly/execute, read/write and rarely read/write/execute.

    Virtual memory is the use of secondary storage to simulate physical memory. The program loader reads the executable file and builds the address space on disk. For example, on some systems the executable file itself became the page file for code and data.

    Once the program is loaded, the address space consists of pages that are valid to the operating system but have no mapping to physical addresses.

    When the program starts running it accesses valid pages without mappings that results in page faults. The operating system page fault handler finds where the page is stored in secondary storage, maps the page to a physical page frame, and loads the data into the page.

    So if a process is going to execute and it has no page in main memory,how will Instruction register store its first instruction which will executed by CPU resulting in further page faults?

    The starting instruction is specified in the executable. That value gets loaded into a register. There is no first instruction in memory. When the program tries to execute its first instruction, it gets a page fault.