You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

189 lines
6.1 KiB

/*
* Copyright (c) 2013-2014, ARM Limited and Contributors. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer.
*
* Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* Neither the name of ARM nor the names of its contributors may be used
* to endorse or promote products derived from this software without specific
* prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
#include <platform_def.h>
OUTPUT_FORMAT(PLATFORM_LINKER_FORMAT)
OUTPUT_ARCH(PLATFORM_LINKER_ARCH)
ENTRY(bl31_entrypoint)
MEMORY {
RAM (rwx): ORIGIN = BL31_BASE, LENGTH = BL31_LIMIT - BL31_BASE
}
SECTIONS
{
. = BL31_BASE;
ASSERT(. == ALIGN(4096),
"BL31_BASE address is not aligned on a page boundary.")
ro . : {
__RO_START__ = .;
*bl31_entrypoint.o(.text*)
*(.text*)
*(.rodata*)
/* Ensure 8-byte alignment for descriptors and ensure inclusion */
. = ALIGN(8);
__RT_SVC_DESCS_START__ = .;
KEEP(*(rt_svc_descs))
__RT_SVC_DESCS_END__ = .;
/*
* Ensure 8-byte alignment for cpu_ops so that its fields are also
* aligned. Also ensure cpu_ops inclusion.
*/
. = ALIGN(8);
__CPU_OPS_START__ = .;
KEEP(*(cpu_ops))
__CPU_OPS_END__ = .;
*(.vectors)
__RO_END_UNALIGNED__ = .;
/*
* Memory page(s) mapped to this section will be marked as read-only,
* executable. No RW data from the next section must creep in.
* Ensure the rest of the current memory page is unused.
*/
. = NEXT(4096);
__RO_END__ = .;
} >RAM
ASSERT(__CPU_OPS_END__ > __CPU_OPS_START__,
"cpu_ops not defined for this platform.")
Make generic code work in presence of system caches On the ARMv8 architecture, cache maintenance operations by set/way on the last level of integrated cache do not affect the system cache. This means that such a flush or clean operation could result in the data being pushed out to the system cache rather than main memory. Another CPU could access this data before it enables its data cache or MMU. Such accesses could be serviced from the main memory instead of the system cache. If the data in the sysem cache has not yet been flushed or evicted to main memory then there could be a loss of coherency. The only mechanism to guarantee that the main memory will be updated is to use cache maintenance operations to the PoC by MVA(See section D3.4.11 (System level caches) of ARMv8-A Reference Manual (Issue A.g/ARM DDI0487A.G). This patch removes the reliance of Trusted Firmware on the flush by set/way operation to ensure visibility of data in the main memory. Cache maintenance operations by MVA are now used instead. The following are the broad category of changes: 1. The RW areas of BL2/BL31/BL32 are invalidated by MVA before the C runtime is initialised. This ensures that any stale cache lines at any level of cache are removed. 2. Updates to global data in runtime firmware (BL31) by the primary CPU are made visible to secondary CPUs using a cache clean operation by MVA. 3. Cache maintenance by set/way operations are only used prior to power down. NOTE: NON-UPSTREAM TRUSTED FIRMWARE CODE SHOULD MAKE EQUIVALENT CHANGES IN ORDER TO FUNCTION CORRECTLY ON PLATFORMS WITH SUPPORT FOR SYSTEM CACHES. Fixes ARM-software/tf-issues#205 Change-Id: I64f1b398de0432813a0e0881d70f8337681f6e9a
9 years ago
/*
* Define a linker symbol to mark start of the RW memory area for this
* image.
*/
__RW_START__ = . ;
.data . : {
__DATA_START__ = .;
*(.data*)
__DATA_END__ = .;
} >RAM
fvp: Reuse BL1 and BL2 memory through image overlaying This patch re-organizes the memory layout on FVP as to give the BL3-2 image as much memory as possible. Considering these two facts: - not all images need to live in memory at the same time. Once in BL3-1, the memory used by BL1 and BL2 can be reclaimed. - when BL2 loads the BL3-1 and BL3-2 images, it only considers the PROGBITS sections of those 2 images. The memory occupied by the NOBITS sections will be touched only at execution of the BL3-x images; Then it is possible to choose the different base addresses such that the NOBITS sections of BL3-1 and BL3-2 overlay BL1 and BL2. On FVP we choose to put: - BL1 and BL3-1 at the top of the Trusted RAM, with BL3-1 NOBITS sections overlaying BL1; - BL3-2 at the bottom of the Trusted RAM, with its NOBITS sections overlaying BL2; This is illustrated by the following diagram: 0x0404_0000 ------------ ------------------ | BL1 | &lt;= | BL3-1 NOBITS | ------------ &lt;= ------------------ | | &lt;= | BL3-1 PROGBITS | ------------ ------------------ | BL2 | &lt;= | BL3-2 NOBITS | ------------ &lt;= ------------------ | | &lt;= | BL3-2 PROGBITS | 0x0400_0000 ------------ ------------------ New platform-specific constants have been introduced to easily check at link time that BL3-1 and BL3-2 PROGBITS sections don&#39;t overwrite BL1 and BL2. These are optional and the platform code is free to define them or not. If not defined, the linker won&#39;t attempt to check image overlaying. Fixes ARM-software/tf-issues#117 Change-Id: I5981d1c3d66ee70eaac8bd052630c9ac6dd8b042
11 years ago
#ifdef BL31_PROGBITS_LIMIT
ASSERT(. <= BL31_PROGBITS_LIMIT, "BL3-1 progbits has exceeded its limit.")
#endif
stacks (NOLOAD) : {
__STACKS_START__ = .;
*(tzfw_normal_stacks)
__STACKS_END__ = .;
} >RAM
/*
* The .bss section gets initialised to 0 at runtime.
* Its base address must be 16-byte aligned.
*/
Re-design bakery lock memory allocation and algorithm This patch unifies the bakery lock api&#39;s across coherent and normal memory implementation of locks by using same data type `bakery_lock_t` and similar arguments to functions. A separate section `bakery_lock` has been created and used to allocate memory for bakery locks using `DEFINE_BAKERY_LOCK`. When locks are allocated in normal memory, each lock for a core has to spread across multiple cache lines. By using the total size allocated in a separate cache line for a single core at compile time, the memory for other core locks is allocated at link time by multiplying the single core locks size with (PLATFORM_CORE_COUNT - 1). The normal memory lock algorithm now uses lock address instead of the `id` in the per_cpu_data. For locks allocated in coherent memory, it moves locks from tzfw_coherent_memory to bakery_lock section. The bakery locks are allocated as part of bss or in coherent memory depending on usage of coherent memory. Both these regions are initialised to zero as part of run_time_init before locks are used. Hence, bakery_lock_init() is made an empty function as the lock memory is already initialised to zero. The above design lead to the removal of psci bakery locks from non_cpu_power_pd_node to psci_locks. NOTE: THE BAKERY LOCK API WHEN USE_COHERENT_MEM IS NOT SET HAS CHANGED. THIS IS A BREAKING CHANGE FOR ALL PLATFORM PORTS THAT ALLOCATE BAKERY LOCKS IN NORMAL MEMORY. Change-Id: Ic3751c0066b8032dcbf9d88f1d4dc73d15f61d8b
9 years ago
.bss (NOLOAD) : ALIGN(16) {
__BSS_START__ = .;
*(.bss*)
*(COMMON)
Re-design bakery lock memory allocation and algorithm This patch unifies the bakery lock api&#39;s across coherent and normal memory implementation of locks by using same data type `bakery_lock_t` and similar arguments to functions. A separate section `bakery_lock` has been created and used to allocate memory for bakery locks using `DEFINE_BAKERY_LOCK`. When locks are allocated in normal memory, each lock for a core has to spread across multiple cache lines. By using the total size allocated in a separate cache line for a single core at compile time, the memory for other core locks is allocated at link time by multiplying the single core locks size with (PLATFORM_CORE_COUNT - 1). The normal memory lock algorithm now uses lock address instead of the `id` in the per_cpu_data. For locks allocated in coherent memory, it moves locks from tzfw_coherent_memory to bakery_lock section. The bakery locks are allocated as part of bss or in coherent memory depending on usage of coherent memory. Both these regions are initialised to zero as part of run_time_init before locks are used. Hence, bakery_lock_init() is made an empty function as the lock memory is already initialised to zero. The above design lead to the removal of psci bakery locks from non_cpu_power_pd_node to psci_locks. NOTE: THE BAKERY LOCK API WHEN USE_COHERENT_MEM IS NOT SET HAS CHANGED. THIS IS A BREAKING CHANGE FOR ALL PLATFORM PORTS THAT ALLOCATE BAKERY LOCKS IN NORMAL MEMORY. Change-Id: Ic3751c0066b8032dcbf9d88f1d4dc73d15f61d8b
9 years ago
#if !USE_COHERENT_MEM
/*
* Bakery locks are stored in normal .bss memory
*
* Each lock's data is spread across multiple cache lines, one per CPU,
* but multiple locks can share the same cache line.
* The compiler will allocate enough memory for one CPU's bakery locks,
* the remaining cache lines are allocated by the linker script
*/
. = ALIGN(CACHE_WRITEBACK_GRANULE);
__BAKERY_LOCK_START__ = .;
*(bakery_lock)
. = ALIGN(CACHE_WRITEBACK_GRANULE);
__PERCPU_BAKERY_LOCK_SIZE__ = ABSOLUTE(. - __BAKERY_LOCK_START__);
Re-design bakery lock memory allocation and algorithm This patch unifies the bakery lock api&#39;s across coherent and normal memory implementation of locks by using same data type `bakery_lock_t` and similar arguments to functions. A separate section `bakery_lock` has been created and used to allocate memory for bakery locks using `DEFINE_BAKERY_LOCK`. When locks are allocated in normal memory, each lock for a core has to spread across multiple cache lines. By using the total size allocated in a separate cache line for a single core at compile time, the memory for other core locks is allocated at link time by multiplying the single core locks size with (PLATFORM_CORE_COUNT - 1). The normal memory lock algorithm now uses lock address instead of the `id` in the per_cpu_data. For locks allocated in coherent memory, it moves locks from tzfw_coherent_memory to bakery_lock section. The bakery locks are allocated as part of bss or in coherent memory depending on usage of coherent memory. Both these regions are initialised to zero as part of run_time_init before locks are used. Hence, bakery_lock_init() is made an empty function as the lock memory is already initialised to zero. The above design lead to the removal of psci bakery locks from non_cpu_power_pd_node to psci_locks. NOTE: THE BAKERY LOCK API WHEN USE_COHERENT_MEM IS NOT SET HAS CHANGED. THIS IS A BREAKING CHANGE FOR ALL PLATFORM PORTS THAT ALLOCATE BAKERY LOCKS IN NORMAL MEMORY. Change-Id: Ic3751c0066b8032dcbf9d88f1d4dc73d15f61d8b
9 years ago
. = . + (__PERCPU_BAKERY_LOCK_SIZE__ * (PLATFORM_CORE_COUNT - 1));
__BAKERY_LOCK_END__ = .;
#ifdef PLAT_PERCPU_BAKERY_LOCK_SIZE
ASSERT(__PERCPU_BAKERY_LOCK_SIZE__ == PLAT_PERCPU_BAKERY_LOCK_SIZE,
"PLAT_PERCPU_BAKERY_LOCK_SIZE does not match bakery lock requirements");
#endif
#endif
__BSS_END__ = .;
} >RAM
/*
* The xlat_table section is for full, aligned page tables (4K).
* Removing them from .bss avoids forcing 4K alignment on
* the .bss section and eliminates the unecessary zero init
*/
xlat_table (NOLOAD) : {
*(xlat_table)
} >RAM
#if USE_COHERENT_MEM
/*
* The base address of the coherent memory section must be page-aligned (4K)
* to guarantee that the coherent data are stored on their own pages and
* are not mixed with normal data. This is required to set up the correct
* memory attributes for the coherent data page tables.
*/
coherent_ram (NOLOAD) : ALIGN(4096) {
__COHERENT_RAM_START__ = .;
Re-design bakery lock memory allocation and algorithm This patch unifies the bakery lock api&#39;s across coherent and normal memory implementation of locks by using same data type `bakery_lock_t` and similar arguments to functions. A separate section `bakery_lock` has been created and used to allocate memory for bakery locks using `DEFINE_BAKERY_LOCK`. When locks are allocated in normal memory, each lock for a core has to spread across multiple cache lines. By using the total size allocated in a separate cache line for a single core at compile time, the memory for other core locks is allocated at link time by multiplying the single core locks size with (PLATFORM_CORE_COUNT - 1). The normal memory lock algorithm now uses lock address instead of the `id` in the per_cpu_data. For locks allocated in coherent memory, it moves locks from tzfw_coherent_memory to bakery_lock section. The bakery locks are allocated as part of bss or in coherent memory depending on usage of coherent memory. Both these regions are initialised to zero as part of run_time_init before locks are used. Hence, bakery_lock_init() is made an empty function as the lock memory is already initialised to zero. The above design lead to the removal of psci bakery locks from non_cpu_power_pd_node to psci_locks. NOTE: THE BAKERY LOCK API WHEN USE_COHERENT_MEM IS NOT SET HAS CHANGED. THIS IS A BREAKING CHANGE FOR ALL PLATFORM PORTS THAT ALLOCATE BAKERY LOCKS IN NORMAL MEMORY. Change-Id: Ic3751c0066b8032dcbf9d88f1d4dc73d15f61d8b
9 years ago
/*
* Bakery locks are stored in coherent memory
*
* Each lock's data is contiguous and fully allocated by the compiler
*/
*(bakery_lock)
*(tzfw_coherent_mem)
__COHERENT_RAM_END_UNALIGNED__ = .;
/*
* Memory page(s) mapped to this section will be marked
* as device memory. No other unexpected data must creep in.
* Ensure the rest of the current memory page is unused.
*/
. = NEXT(4096);
__COHERENT_RAM_END__ = .;
} >RAM
#endif
Make generic code work in presence of system caches On the ARMv8 architecture, cache maintenance operations by set/way on the last level of integrated cache do not affect the system cache. This means that such a flush or clean operation could result in the data being pushed out to the system cache rather than main memory. Another CPU could access this data before it enables its data cache or MMU. Such accesses could be serviced from the main memory instead of the system cache. If the data in the sysem cache has not yet been flushed or evicted to main memory then there could be a loss of coherency. The only mechanism to guarantee that the main memory will be updated is to use cache maintenance operations to the PoC by MVA(See section D3.4.11 (System level caches) of ARMv8-A Reference Manual (Issue A.g/ARM DDI0487A.G). This patch removes the reliance of Trusted Firmware on the flush by set/way operation to ensure visibility of data in the main memory. Cache maintenance operations by MVA are now used instead. The following are the broad category of changes: 1. The RW areas of BL2/BL31/BL32 are invalidated by MVA before the C runtime is initialised. This ensures that any stale cache lines at any level of cache are removed. 2. Updates to global data in runtime firmware (BL31) by the primary CPU are made visible to secondary CPUs using a cache clean operation by MVA. 3. Cache maintenance by set/way operations are only used prior to power down. NOTE: NON-UPSTREAM TRUSTED FIRMWARE CODE SHOULD MAKE EQUIVALENT CHANGES IN ORDER TO FUNCTION CORRECTLY ON PLATFORMS WITH SUPPORT FOR SYSTEM CACHES. Fixes ARM-software/tf-issues#205 Change-Id: I64f1b398de0432813a0e0881d70f8337681f6e9a
9 years ago
/*
* Define a linker symbol to mark end of the RW memory area for this
* image.
*/
__RW_END__ = .;
__BL31_END__ = .;
__BSS_SIZE__ = SIZEOF(.bss);
#if USE_COHERENT_MEM
__COHERENT_RAM_UNALIGNED_SIZE__ =
__COHERENT_RAM_END_UNALIGNED__ - __COHERENT_RAM_START__;
#endif
ASSERT(. <= BL31_LIMIT, "BL3-1 image has exceeded its limit.")
}