diff --git a/docs/porting-guide.rst b/docs/porting-guide.rst
index 4f1638a..f1a26f4 100644
--- a/docs/porting-guide.rst
+++ b/docs/porting-guide.rst
@@ -2550,9 +2550,6 @@
 Crash Reporting mechanism (in BL31)
 -----------------------------------
 
-NOTE: This section assumes that your platform is enabling the MULTI_CONSOLE_API
-flag in its platform.mk. Not using this flag is deprecated for new platforms.
-
 BL31 implements a crash reporting mechanism which prints the various registers
 of the CPU to enable quick crash analysis and debugging. This mechanism relies
 on the platform implementating ``plat_crash_console_init``,
@@ -2564,15 +2561,18 @@
 output to be routed over the normal console infrastructure and get printed on
 consoles configured to output in crash state. ``console_set_scope()`` can be
 used to control whether a console is used for crash output.
+NOTE: Platforms are responsible for making sure that they only mark consoles for
+use in the crash scope that are able to support this, i.e. that are written in
+assembly and conform with the register clobber rules for putc() (x0-x2, x16-x17)
+and flush() (x0-x3, x16-x17) crash callbacks.
 
 In some cases (such as debugging very early crashes that happen before the
 normal boot console can be set up), platforms may want to control crash output
-more explicitly. For these, the following functions can be overridden by
-platform code. They are executed outside of a C environment and without a stack.
-
-If this behaviour is not desirable, the platform may implement functions that
-redirect the prints to the console driver (``console_xxx_core_init``, etc). Most
-platforms (including Arm platforms) do this and they can be used as an example.
+more explicitly. These platforms may instead provide custom implementations for
+these. They are executed outside of a C environment and without a stack. Many
+console drivers provide functions named ``console_xxx_core_init/putc/flush``
+that are designed to be used by these functions. See Arm platforms (like juno)
+for an example of this.
 
 Function : plat\_crash\_console\_init [mandatory]
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -2586,28 +2586,6 @@
 console. It must only use the general purpose registers x0 through x7 to do the
 initialization and returns 1 on success.
 
-When using the sample implementation, if you are trying to debug crashes before
-the console driver would normally get registered, you can use this to register a
-driver from assembly with hardcoded parameters. For example, you could register
-the 16550 driver like this:
-
-::
-
-    .section .data.crash_console      /* Reserve space for console structure */
-    crash_console:
-    .zero 6 * 8                       /* console_16550_t has 6 8-byte words */
-    func plat_crash_console_init
-        ldr     x0, =YOUR_16550_BASE_ADDR
-        ldr     x1, =YOUR_16550_SRCCLK_IN_HZ
-        ldr     x2, =YOUR_16550_TARGET_BAUD_RATE
-        adrp    x3, crash_console
-        add     x3, x3, :lo12:crash_console
-        b       console_16550_register  /* tail call, returns 1 on success */
-    endfunc plat_crash_console_init
-
-If you're trying to debug crashes in BL1, you can call the
-``console_xxx_core_init`` function exported by some console drivers from here.
-
 Function : plat\_crash\_console\_putc [mandatory]
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -2621,12 +2599,6 @@
 x2 to do its work. The parameter and the return value are in general purpose
 register x0.
 
-If you have registered a normal console driver in ``plat_crash_console_init``,
-you can keep the sample implementation here (which calls ``console_putc()``).
-
-If you're trying to debug crashes in BL1, you can call the
-``console_xxx_core_putc`` function exported by some console drivers from here.
-
 Function : plat\_crash\_console\_flush [mandatory]
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -2640,12 +2612,6 @@
 registers x0 through x5 to do its work. The return value is 0 on successful
 completion; otherwise the return value is -1.
 
-If you have registered a normal console driver in ``plat_crash_console_init``,
-you can keep the sample implementation here (which calls ``console_flush()``).
-
-If you're trying to debug crashes in BL1, you can call the console_xx_core_flush
-function exported by some console drivers from here.
-
 External Abort handling and RAS Support
 ---------------------------------------
 
diff --git a/drivers/console/aarch64/multi_console.S b/drivers/console/aarch64/multi_console.S
index 7f076c6..95423b0 100644
--- a/drivers/console/aarch64/multi_console.S
+++ b/drivers/console/aarch64/multi_console.S
@@ -16,6 +16,7 @@
 	.globl	console_putc
 	.globl	console_getc
 	.globl	console_flush
+	.globl	console_list
 
 	/*
 	 *  The console list pointer is in the data section and not in
diff --git a/plat/common/aarch64/crash_console_helpers.S b/plat/common/aarch64/crash_console_helpers.S
index 55e7abb..8f8ca11 100644
--- a/plat/common/aarch64/crash_console_helpers.S
+++ b/plat/common/aarch64/crash_console_helpers.S
@@ -20,53 +20,163 @@
 #error "This crash console implementation only works with the MULTI_CONSOLE_API!"
 #endif
 
-	/* -----------------------------------------------------
+	/*
+	 * Spinlock to syncronize access to crash_console_triggered. We cannot
+	 * acquire spinlocks when the cache is disabled, so in some cases (like
+	 * late during CPU suspend) some risk remains.
+	 */
+.section .data.crash_console_spinlock
+	define_asm_spinlock crash_console_spinlock
+
+	/*
+	 * Flag to make sure that only one CPU can write a crash dump even if
+	 * multiple crash at the same time. Interleaving crash dumps on the same
+	 * console would just make the output unreadable, so it's better to only
+	 * get a single but uncorrupted dump. This also means that we don't have
+	 * to duplicate the reg_stash below for each CPU.
+	 */
+.section .data.crash_console_triggered
+	crash_console_triggered: .byte 0
+
+	/*
+	 * Space to stash away some register values while we're calling into
+	 * console drivers and don't have a real stack available. We need x14,
+	 * x15 and x30 for bookkeeping within the plat_crash_console functions
+	 * themselves, and some console drivers use x16 and x17 as additional
+	 * scratch space that is not preserved by the main crash reporting
+	 * framework. (Note that x16 and x17 should really never be expected to
+	 * retain their values across any function call, even between carefully
+	 * designed assembly functions, since the linker is always free to
+	 * insert a function call veneer that uses these registers as scratch
+	 * space at any time. The current crash reporting framework doesn't
+	 * really respect that, but since TF is usually linked as a single
+	 * contiguous binary of less than 128MB, it seems to work in practice.)
+	 */
+.section .data.crash_console_reg_stash
+	.align 3
+	crash_console_reg_stash: .quad 0, 0, 0, 0, 0
+
+	/* --------------------------------------------------------------------
 	 * int plat_crash_console_init(void)
-	 * Use normal console by default. Switch it to crash
-	 * mode so serial consoles become active again.
-	 * NOTE: This default implementation will only work for
-	 * crashes that occur after a normal console (marked
-	 * valid for the crash state) has been registered with
-	 * the console framework. To debug crashes that occur
-	 * earlier, the platform has to override these functions
-	 * with an implementation that initializes a console
-	 * driver with hardcoded parameters. See
-	 * docs/porting-guide.rst for more information.
-	 * -----------------------------------------------------
+	 * Takes the crash console spinlock (if possible) and checks the trigger
+	 * flag to make sure we're the first CPU to dump. If not, return an
+	 * error (so crash dumping will fail but the CPU will still call
+	 * plat_panic_handler() which may do important platform-specific tasks
+	 * that may be needed on all crashing CPUs). In either case, the lock
+	 * will be released so other CPUs can make forward progress on this.
+	 * Clobbers: x0 - x4, x30
+	 * --------------------------------------------------------------------
 	 */
 func plat_crash_console_init
-#if defined(IMAGE_BL1)
-	/*
-	 * BL1 code can possibly crash so early that the data segment is not yet
-	 * accessible. Don't risk undefined behavior by trying to run the normal
-	 * console framework. Platforms that want to debug BL1 will need to
-	 * override this with custom functions that can run from registers only.
-	 */
-	mov	x0, #0
-	ret
-#else	/* IMAGE_BL1 */
-	mov	x3, x30
-	mov	x0, #CONSOLE_FLAG_CRASH
-	bl	console_switch_state
+#if defined(IMAGE_BL31)
+	mov	x4, x30		/* x3 and x4 are not clobbered by spin_lock() */
+	mov	x3, #0		/* return value */
+
+	mrs	x1, sctlr_el3
+	tst	x1, #SCTLR_C_BIT
+	beq	skip_spinlock	/* can't synchronize when cache disabled */
+
+	adrp	x0, crash_console_spinlock
+	add	x0, x0, :lo12:crash_console_spinlock
+	bl	spin_lock
+
+skip_spinlock:
+	adrp	x1, crash_console_triggered
+	add	x1, x1, :lo12:crash_console_triggered
+	ldarb	w2, [x1]
+	cmp	w2, #0
+	bne	init_error
+
+	mov	x3, #1		/* set return value to success */
+	stlrb	w3, [x1]
+
+init_error:
+	bl	spin_unlock	/* harmless if we didn't acquire the lock */
+	mov	x0, x3
+	ret	x4
+#else	/* Only one CPU in BL1/BL2, no need to synchronize anything */
 	mov	x0, #1
-	ret	x3
+	ret
 #endif
 endfunc plat_crash_console_init
 
-	/* -----------------------------------------------------
-	 * void plat_crash_console_putc(int character)
-	 * Output through the normal console by default.
-	 * -----------------------------------------------------
+	/* --------------------------------------------------------------------
+	 * int plat_crash_console_putc(char c)
+	 * Prints the character on all consoles registered with the console
+	 * framework that have CONSOLE_FLAG_CRASH set. Note that this is only
+	 * helpful for crashes that occur after the platform intialization code
+	 * has registered a console. Platforms using this implementation need to
+	 * ensure that all console drivers they use that have the CRASH flag set
+	 * support this (i.e. are written in assembly and comply to the register
+	 * clobber requirements of plat_crash_console_putc().
+	 * --------------------------------------------------------------------
 	 */
 func plat_crash_console_putc
-	b	console_putc
+	adrp	x1, crash_console_reg_stash
+	add	x1, x1, :lo12:crash_console_reg_stash
+	stp	x14, x15, [x1]
+	stp	x16, x17, [x1, #16]
+	str	x30, [x1, #32]
+
+	mov	w14, w0				/* W14 = character to print */
+	adrp	x15, console_list
+	ldr	x15, [x15, :lo12:console_list]	/* X15 = first console struct */
+
+putc_loop:
+	cbz	x15, putc_done
+	ldr	w1, [x15, #CONSOLE_T_FLAGS]
+	tst	w1, #CONSOLE_FLAG_CRASH
+	b.eq	putc_continue
+	ldr	x2, [x15, #CONSOLE_T_PUTC]
+	cbz	x2, putc_continue
+	mov	x1, x15
+	blr	x2
+	mov	w0, w14
+putc_continue:
+	ldr	x15, [x15]			/* X15 = next struct */
+	b	putc_loop
+
+putc_done:
+	adrp	x1, crash_console_reg_stash
+	add	x1, x1, :lo12:crash_console_reg_stash
+	ldp	x14, x15, [x1]
+	ldp	x16, x17, [x1, #16]
+	ldr	x30, [x1, #32]
+	ret
 endfunc plat_crash_console_putc
 
-	/* -----------------------------------------------------
-	 * void plat_crash_console_flush(void)
-	 * Flush normal console by default.
-	 * -----------------------------------------------------
+	/* --------------------------------------------------------------------
+	 * int plat_crash_console_flush(char c)
+	 * Flushes all consoles registered with the console framework that have
+	 * CONSOLE_FLAG_CRASH set. Same requirements as putc().
+	 * --------------------------------------------------------------------
 	 */
 func plat_crash_console_flush
-	b	console_flush
+	adrp	x1, crash_console_reg_stash
+	add	x1, x1, :lo12:crash_console_reg_stash
+	stp	x30, x15, [x1]
+	stp	x16, x17, [x1, #16]
+
+	adrp	x15, console_list
+	ldr	x15, [x15, :lo12:console_list]	/* X15 = first console struct */
+
+flush_loop:
+	cbz	x15, flush_done
+	ldr	w1, [x15, #CONSOLE_T_FLAGS]
+	tst	w1, #CONSOLE_FLAG_CRASH
+	b.eq	flush_continue
+	ldr	x2, [x15, #CONSOLE_T_FLUSH]
+	cbz	x2, flush_continue
+	mov	x0, x15
+	blr	x2
+flush_continue:
+	ldr	x15, [x15]			/* X15 = next struct */
+	b	flush_loop
+
+flush_done:
+	adrp	x1, crash_console_reg_stash
+	add	x1, x1, :lo12:crash_console_reg_stash
+	ldp	x30, x15, [x1]
+	ldp	x16, x17, [x1, #16]
+	ret
 endfunc plat_crash_console_flush