summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/net/bpf_jit_64.S
diff options
context:
space:
mode:
authorJames Bottomley <JBottomley@Parallels.com>2012-05-21 12:17:30 +0100
committerJames Bottomley <JBottomley@Parallels.com>2012-05-21 12:17:30 +0100
commite34693336564f02b3e2cc09d8b872aef22a154e9 (patch)
tree09f51f10f9406042f9176e39b4dc8de850ba712e /arch/powerpc/net/bpf_jit_64.S
parent76b311fdbdd2e16e5d39cd496a67aa1a1b948914 (diff)
parentde2eb4d5c5c25e8fb75d1e19092f24b83cb7d8d5 (diff)
downloadlinux-e34693336564f02b3e2cc09d8b872aef22a154e9.tar.bz2
Merge tag 'isci-for-3.5' into misc
isci update for 3.5 1/ Rework remote-node-context (RNC) handling for proper management of the silicon state machine in error handling and hot-plug conditions. Further details below, suffice to say if the RNC is mismanaged the silicon state machines may lock up. 2/ Refactor the initialization code to be reused for suspend/resume support 3/ Miscellaneous bug fixes to address discovery issues and hardware compatibility. RNC rework details from Jeff Skirvin: In the controller, devices as they appear on a SAS domain (or direct-attached SATA devices) are represented by memory structures known as "Remote Node Contexts" (RNCs). These structures are transferred from main memory to the controller using a set of register commands; these commands include setting up the context ("posting"), removing the context ("invalidating"), and commands to control the scheduling of commands and connections to that remote device ("suspensions" and "resumptions"). There is a similar path to control RNC scheduling from the protocol engine, which interprets the results of command and data transmission and reception. In general, the controller chooses among non-suspended RNCs to find one that has work requiring scheduling the transmission of command and data frames to a target. Likewise, when a target tries to return data back to the initiator, the state of the RNC is used by the controller to determine how to treat the incoming request. As an example, if the RNC is in the state "TX/RX Suspended", incoming SSP connection requests from the target will be rejected by the controller hardware. When an RNC is "TX Suspended", it will not be selected by the controller hardware to start outgoing command or data operations (with certain priority-based exceptions). As mentioned above, there are two sources for management of the RNC states: commands from driver software, and the result of transmission and reception conditions of commands and data signaled by the controller hardware. As an example of the latter, if an outgoing SSP command ends with a OPEN_REJECT(BAD_DESTINATION) status, the RNC state will transition to the "TX Suspended" state, and this is signaled by the controller hardware in the status to the completion of the pending command as well as signaled in a controller hardware event. Examples of the former are included in the patch changelogs. Driver software is required to suspend the RNC in a "TX/RX Suspended" condition before any outstanding commands can be terminated. Failure to guarantee this can lead to a complete hardware hang condition. Earlier versions of the driver software did not guarantee that an RNC was correctly managed before I/O termination, and so operated in an unsafe way. Further, the driver performed unnecessary contortions to preserve the remote device command state and so was more complicated than it needed to be. A simplifying driver assumption is that once an I/O has entered the error handler path without having completed in the target, the requirement on the driver is that all use of the sas_task must end. Beyond that, recovery of operation is dependent on libsas and other components to reset, rediscover and reconfigure the device before normal operation can restart. In the driver, this simplifying assumption meant that the RNC management could be reduced to entry into the suspended state, terminating the targeted I/O request, and resuming the RNC as needed for device-specific management such as an SSP Abort Task or LUN Reset Management request.
Diffstat (limited to 'arch/powerpc/net/bpf_jit_64.S')
-rw-r--r--arch/powerpc/net/bpf_jit_64.S108
1 files changed, 95 insertions, 13 deletions
diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
index ff4506e85cce..55ba3855a97f 100644
--- a/arch/powerpc/net/bpf_jit_64.S
+++ b/arch/powerpc/net/bpf_jit_64.S
@@ -31,14 +31,13 @@
* then branch directly to slow_path_XXX if required. (In fact, could
* load a spare GPR with the address of slow_path_generic and pass size
* as an argument, making the call site a mtlr, li and bllr.)
- *
- * Technically, the "is addr < 0" check is unnecessary & slowing down
- * the ABS path, as it's statically checked on generation.
*/
.globl sk_load_word
sk_load_word:
cmpdi r_addr, 0
- blt bpf_error
+ blt bpf_slow_path_word_neg
+ .globl sk_load_word_positive_offset
+sk_load_word_positive_offset:
/* Are we accessing past headlen? */
subi r_scratch1, r_HL, 4
cmpd r_scratch1, r_addr
@@ -51,7 +50,9 @@ sk_load_word:
.globl sk_load_half
sk_load_half:
cmpdi r_addr, 0
- blt bpf_error
+ blt bpf_slow_path_half_neg
+ .globl sk_load_half_positive_offset
+sk_load_half_positive_offset:
subi r_scratch1, r_HL, 2
cmpd r_scratch1, r_addr
blt bpf_slow_path_half
@@ -61,7 +62,9 @@ sk_load_half:
.globl sk_load_byte
sk_load_byte:
cmpdi r_addr, 0
- blt bpf_error
+ blt bpf_slow_path_byte_neg
+ .globl sk_load_byte_positive_offset
+sk_load_byte_positive_offset:
cmpd r_HL, r_addr
ble bpf_slow_path_byte
lbzx r_A, r_D, r_addr
@@ -69,22 +72,20 @@ sk_load_byte:
/*
* BPF_S_LDX_B_MSH: ldxb 4*([offset]&0xf)
- * r_addr is the offset value, already known positive
+ * r_addr is the offset value
*/
.globl sk_load_byte_msh
sk_load_byte_msh:
+ cmpdi r_addr, 0
+ blt bpf_slow_path_byte_msh_neg
+ .globl sk_load_byte_msh_positive_offset
+sk_load_byte_msh_positive_offset:
cmpd r_HL, r_addr
ble bpf_slow_path_byte_msh
lbzx r_X, r_D, r_addr
rlwinm r_X, r_X, 2, 32-4-2, 31-2
blr
-bpf_error:
- /* Entered with cr0 = lt */
- li r3, 0
- /* Generated code will 'blt epilogue', returning 0. */
- blr
-
/* Call out to skb_copy_bits:
* We'll need to back up our volatile regs first; we have
* local variable space at r1+(BPF_PPC_STACK_BASIC).
@@ -136,3 +137,84 @@ bpf_slow_path_byte_msh:
lbz r_X, BPF_PPC_STACK_BASIC+(2*8)(r1)
rlwinm r_X, r_X, 2, 32-4-2, 31-2
blr
+
+/* Call out to bpf_internal_load_pointer_neg_helper:
+ * We'll need to back up our volatile regs first; we have
+ * local variable space at r1+(BPF_PPC_STACK_BASIC).
+ * Allocate a new stack frame here to remain ABI-compliant in
+ * stashing LR.
+ */
+#define sk_negative_common(SIZE) \
+ mflr r0; \
+ std r0, 16(r1); \
+ /* R3 goes in parameter space of caller's frame */ \
+ std r_skb, (BPF_PPC_STACKFRAME+48)(r1); \
+ std r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1); \
+ std r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1); \
+ stdu r1, -BPF_PPC_SLOWPATH_FRAME(r1); \
+ /* R3 = r_skb, as passed */ \
+ mr r4, r_addr; \
+ li r5, SIZE; \
+ bl bpf_internal_load_pointer_neg_helper; \
+ /* R3 != 0 on success */ \
+ addi r1, r1, BPF_PPC_SLOWPATH_FRAME; \
+ ld r0, 16(r1); \
+ ld r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1); \
+ ld r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1); \
+ mtlr r0; \
+ cmpldi r3, 0; \
+ beq bpf_error_slow; /* cr0 = EQ */ \
+ mr r_addr, r3; \
+ ld r_skb, (BPF_PPC_STACKFRAME+48)(r1); \
+ /* Great success! */
+
+bpf_slow_path_word_neg:
+ lis r_scratch1,-32 /* SKF_LL_OFF */
+ cmpd r_addr, r_scratch1 /* addr < SKF_* */
+ blt bpf_error /* cr0 = LT */
+ .globl sk_load_word_negative_offset
+sk_load_word_negative_offset:
+ sk_negative_common(4)
+ lwz r_A, 0(r_addr)
+ blr
+
+bpf_slow_path_half_neg:
+ lis r_scratch1,-32 /* SKF_LL_OFF */
+ cmpd r_addr, r_scratch1 /* addr < SKF_* */
+ blt bpf_error /* cr0 = LT */
+ .globl sk_load_half_negative_offset
+sk_load_half_negative_offset:
+ sk_negative_common(2)
+ lhz r_A, 0(r_addr)
+ blr
+
+bpf_slow_path_byte_neg:
+ lis r_scratch1,-32 /* SKF_LL_OFF */
+ cmpd r_addr, r_scratch1 /* addr < SKF_* */
+ blt bpf_error /* cr0 = LT */
+ .globl sk_load_byte_negative_offset
+sk_load_byte_negative_offset:
+ sk_negative_common(1)
+ lbz r_A, 0(r_addr)
+ blr
+
+bpf_slow_path_byte_msh_neg:
+ lis r_scratch1,-32 /* SKF_LL_OFF */
+ cmpd r_addr, r_scratch1 /* addr < SKF_* */
+ blt bpf_error /* cr0 = LT */
+ .globl sk_load_byte_msh_negative_offset
+sk_load_byte_msh_negative_offset:
+ sk_negative_common(1)
+ lbz r_X, 0(r_addr)
+ rlwinm r_X, r_X, 2, 32-4-2, 31-2
+ blr
+
+bpf_error_slow:
+ /* fabricate a cr0 = lt */
+ li r_scratch1, -1
+ cmpdi r_scratch1, 0
+bpf_error:
+ /* Entered with cr0 = lt */
+ li r3, 0
+ /* Generated code will 'blt epilogue', returning 0. */
+ blr