Date:	Wed, 28 Jan 2015 21:38:45 -0800
From:	Darren Hart <dvhart@...radead.org>
To:	Bryan O'Donoghue <pure.logic@...us-software.ie>
Cc:	tglx@...utronix.de, mingo@...hat.com, hpa@...or.com,
	x86@...nel.org, andy.shevchenko@...il.com,
	boon.leong.ong@...el.com, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 1/2] x86: Add Isolated Memory Regions for Quark X1000

On Wed, Jan 28, 2015 at 06:36:25PM +0000, Bryan O'Donoghue wrote:
> Intel's Quark X1000 SoC contains a set of registers called Isolated Memory
> Regions. IMRs are accessed over the IOSF mailbox interface. IMRs are areas
> carved out of memory that define read/write access rights to the various
> system agents within the Quark system. For a given agent in the system it is
> possible to specify if that agent may read or write an area of memory
> defined by an IMR with a granularity of 1 KiB.
> 
> Quark_SecureBootPRM_330234_001.pdf section 4.5 details the concept of IMRs
> quark-x1000-datasheet.pdf section 12.7.4 details the implementation of IMRs
> in silicon.
> 
> eSRAM flush, CPU Snoop write-only, CPU SMM Mode, CPU non-SMM mode, RMU and
> PCIe Virtual Channels (VC0 and VC1) can have individual read/write access
> masks applied to them for a given memory region in Quark X1000. This
> enables IMRs to treat each memory transaction type listed above on an
> individual basis and to filter appropriately based on the IMR access mask
> for the memory region. Quark supports eight IMRs.
> 
> Since all of the DMA capable SoC components in the X1000 are mapped to VC0
> it is possible to define sections of memory as invalid for DMA write
> operations originating from Ethernet, USB, SD and any other DMA capable
> south-cluster component on VC0. Similarly it is possible to mark kernel
> memory as non-SMM mode read/write only or to mark BIOS runtime memory as SMM
> mode accessible only depending on the particular memory footprint on a given
> system.
> 
> On an IMR violation Quark SoC X1000 systems are configured to reset the
> system, so ensuring that the IMR memory map is consistent with the EFI
> provided memory map is critical to ensure no IMR violations reset the
> system.
> 
> The API for accessing IMRs is based on MTRR code but doesn't provide a /proc
> or /sys interface to manipulate IMRs. Defining the size and extent of IMRs
> is exclusively the domain of in-kernel code.
> 
> Quark firmware sets up a series of locked IMRs around pieces of memory that
> firmware owns such as ACPI runtime data. During boot a series of unlocked
> IMRs are placed around items in memory to guarantee no DMA modification of
> those items can take place. Grub also places an unlocked IMR around the
> kernel boot params data structure and compressed kernel image. It is
> necessary for the kernel to tear down all unlocked IMRs in order to ensure
> that the kernel's view of memory passed via the EFI memory map is consistent
> with the IMR memory map. Without tearing down all unlocked IMRs on boot
> transitory IMRs such as those used to protect the compressed kernel image
> will cause IMR violations and system reboots.
> 
> The IMR init code tears down all unlocked IMRs and sets a protective IMR
> around the kernel .text and .rodata as one contiguous block. This sanitizes
> the IMR memory map with respect to the EFI memory map and protects the
> read-only portions of the kernel from unwarranted DMA access.
> 
> Signed-off-by: Bryan O'Donoghue <pure.logic@...us-software.ie>

Most of my concerns were addressed by V3 or so, but I've followed along and
concur with the subsequent improvements.

Reviewed-by: Darren Hart <dvhart@...ux.intel.com>

-- 
Darren Hart
Intel Open Source Technology Center
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists